Tự động cập nhật: Mỗi 30 phút|187 models · 32 skills

Đồng Bộ Tự Động Model & GitHub Skills

Hệ thống tự động cập nhật định kỳ các Model AI mới ra mắt (OpenRouter, HuggingFace) và kho Open Agent Skills (SKILL.md) công khai trên GitHub, kèm kiểm toán bảo mật tĩnh & mã băm SHA-256 trước khi hiển thị.

Đồng bộ nền tự động bởi máy chủ

Cập nhật Model gần nhất

2026-11-21 13:26 UTC

OpenRouter + HuggingFace

Cập nhật Skill GitHub gần nhất

2026-11-21 13:26 UTC

GitHub SHA-256 + Static Security Audit

Kho GitHub đang theo dõi

anthropics/skills · openai/skills · agentskills/agentskills

Lịch sử Đồng bộ Tự động

Thời điểmPhạm viChế độModelsGitHub SkillsTrạng thái
2026-11-21 13:26 UTCallauto_interval+2 / ~37+0 / ~0ok
2026-11-21 12:56 UTCallauto_interval+2 / ~36+0 / ~0ok
2026-11-21 12:26 UTCallauto_interval+3 / ~36+0 / ~0ok
2026-11-21 11:56 UTCallauto_interval+0 / ~36+0 / ~0ok
2026-11-21 11:26 UTCallauto_interval+1 / ~35+0 / ~0ok
2026-11-21 10:56 UTCallauto_interval+0 / ~35+0 / ~0ok

Chỉ đọc danh mục công khai · Không gửi prompt hay API key ra ngoài.

Phiên bản Danh mục: 2026-11-21-live · 2026-11-21

Cập Nhật Danh Mục & Khám Phá Công Khai

Mọi thay đổi được tổng hợp trực tiếp từ ảnh chụp danh mục có phiên bản (Model, mức giá xác minh, Skill đã kiểm toán bảo mật, tương thích Client, hướng dẫn và bản thiết kế chuẩn). Không dùng AI sinh tóm tắt ảo.

Hiển thị 239 trên 239 bản ghi danh mục thực tế

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

academy-guide (vgit-e4bb5d9) — Verified Source

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I" Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 e2b0b49b8948dace… · Category: Documentation.

Xem chi tiết

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

algorithmic-art (vgit-e4bb5d9) — Verified Source

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather th Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 3d738408cd4b320a… · Category: Design.

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

aspnet-core (vgit-49f948f) — Warning

Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 67f027544508b58c… · Category: Backend Development.

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP4-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP4-MTP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP4-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP8-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP8-MTP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.5-0.8B-decision-MLX-AXQ-MXFP8-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.5-9B-MLX-AXQ-6bit-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-6bit-MTP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-6bit-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP4-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.5-9B-MLX-AXQ-MXFP8-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.6-27B-MLX-AXQ-6bit-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-6bit-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.6-35B-A3B-MLX-AXQ-6bit-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-6bit-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-6bit-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP4-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.6-35B-A3B-MLX-AXQ-MXFP8-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-6bit-MTP — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-6bit-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-6bit-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP4-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/AutomatosX/AX-Swift-1.5-Qwen3.8-27B-MLX-AXQ-MXFP8-MTP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

brand-guidelines (vgit-e4bb5d9) — Verified Source

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 3b70c90cf21615ca… · Category: Design.

Xem chi tiết

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

canvas-design (vgit-e4bb5d9) — Verified Source

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work t Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 8380b714dd3af38d… · Category: Frontend Development.

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

chatgpt-apps (vgit-49f948f) — Warning

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 fc8f07534bed8942… · Category: Frontend Development.

Xem chi tiết

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

claude-api (vgit-e4bb5d9) — Verified Source

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 24d0c6af8ab26236… · Category: Backend Development.

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

cli-creator (vgit-49f948f) — Warning

Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write c Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 fe13c7b09657cf01… · Category: Backend Development.

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

cloudflare-deploy (vgit-49f948f) — Warning

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare. Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 043b9ca105c0f994… · Category: DevOps.

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-Prover-V2-7B-GGUF — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (42ailab/DeepSeek-Prover-V2-7B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/42ailab/DeepSeek-Prover-V2-7B-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-V4-Flash — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (XGYUBNKL/DeepSeek-V4-Flash). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/XGYUBNKL/DeepSeek-V4-Flash (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (xsyh1/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/xsyh1/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-V4.1-Flash-1017-GGUF — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (flaviodelgrosso/DeepSeek-V4.1-Flash-1017-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/flaviodelgrosso/DeepSeek-V4.1-Flash-1017-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-V4.1-Flash-1017-obliterated-MLX-oQ2.5e — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (PocketAiHub/DeepSeek-V4.1-Flash-1017-obliterated-MLX-oQ2.5e). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/PocketAiHub/DeepSeek-V4.1-Flash-1017-obliterated-MLX-oQ2.5e (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-V4.1-Flash-1017-Uncensored — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (OpenUncensored/DeepSeek-V4.1-Flash-1017-Uncensored). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/OpenUncensored/DeepSeek-V4.1-Flash-1017-Uncensored (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

define-goal (vgit-49f948f) — Warning

Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal crea Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 07109577f6c0eb9b… · Category: Software Development.

Xem chi tiết

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

discernment-nudge (vgit-e4bb5d9) — Verified Source

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 9ede92ce3accaf0a… · Category: Documentation.

Xem chi tiết

2026-11-21 · Skill mới · github.com/anthropics/skills · Warning

doc-coauthoring (vgit-e4bb5d9) — Warning

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine conte Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 17c965ee0b464fcd… · Category: Documentation.

Xem chi tiết

2026-11-21 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

docx (vgit-e4bb5d9) — Verified Source

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional docume Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 610a87f06f8104c2… · Category: Documentation.

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · mistral · community_reported

dolphin-2.6-mixtral-8x7b — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (dphn/dolphin-2.6-mixtral-8x7b). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/dphn/dolphin-2.6-mixtral-8x7b (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

dolphin-2.8-gemma-2b — Local Open-Weight Spec (GEMMA)

Open-weight release from HuggingFace Hub (dphn/dolphin-2.8-gemma-2b). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/dphn/dolphin-2.8-gemma-2b (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

dolphin-2.8-gemma-7b — Local Open-Weight Spec (GEMMA)

Open-weight release from HuggingFace Hub (dphn/dolphin-2.8-gemma-7b). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/dphn/dolphin-2.8-gemma-7b (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

dolphin-2.9.1-llama-3-70b — Local Open-Weight Spec (LLAMA3)

Open-weight release from HuggingFace Hub (dphn/dolphin-2.9.1-llama-3-70b). Suitable for private local inference. Hardware: 48GB+ RAM, 42GB disk.

Provenance: https://huggingface.co/dphn/dolphin-2.9.1-llama-3-70b (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · mistral · community_reported

dolphin-2.9.3-mistral-nemo-12b — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (dphn/dolphin-2.9.3-mistral-nemo-12b). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/dphn/dolphin-2.9.3-mistral-nemo-12b (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · mistral · community_reported

Dolphin3.0-Mistral-24B — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (dphn/Dolphin3.0-Mistral-24B). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/dphn/Dolphin3.0-Mistral-24B (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · mistral · community_reported

Dolphin3.0-R1-Mistral-24B — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (dphn/Dolphin3.0-R1-Mistral-24B). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/dphn/Dolphin3.0-R1-Mistral-24B (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · deepseek · community_reported

einsof2-deepseek-prover-v2-stiefel-gguf — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Polydim-Einsof/einsof2-deepseek-prover-v2-stiefel-gguf). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Polydim-Einsof/einsof2-deepseek-prover-v2-stiefel-gguf (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

figma-code-connect-components (vgit-49f948f) — Warning

Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mapp Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 e631e666457ae195… · Category: Frontend Development.

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

figma-create-design-system-rules (vgit-49f948f) — Warning

Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 1193cba86e040996… · Category: Backend Development.

Xem chi tiết

2026-11-21 · Skill mới · github.com/openai/skills · Warning

figma-create-new-file (vgit-49f948f) — Warning

Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Usage — /figma-create-new-file [editorType] [fileName] (e.g. Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 0d3d442acc712fa4… · Category: Design.

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

gemma-3-270m-it-food-extract — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (bhai2000/gemma-3-270m-it-food-extract). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/bhai2000/gemma-3-270m-it-food-extract (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

gemma-4-E2B-it-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/gemma-4-E2B-it-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/gemma-4-E2B-it-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

Gemma-4-E2B-LokalBot-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (stevyhacker/Gemma-4-E2B-LokalBot-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/stevyhacker/Gemma-4-E2B-LokalBot-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

gemma-4-E4B-it-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/gemma-4-E4B-it-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/gemma-4-E4B-it-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

GLM-5.3-Flash-numallama — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (miloserdev/GLM-5.3-Flash-numallama). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/miloserdev/GLM-5.3-Flash-numallama (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

JiRackGemma-37B-alpha-GGUF — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (CMSManhattan/JiRackGemma-37B-alpha-GGUF). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/CMSManhattan/JiRackGemma-37B-alpha-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · google_gemini · community_reported

JiRackGemma-72B-alpha-GGUF — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (CMSManhattan/JiRackGemma-72B-alpha-GGUF). Suitable for private local inference. Hardware: 48GB+ RAM, 42GB disk.

Provenance: https://huggingface.co/CMSManhattan/JiRackGemma-72B-alpha-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

Llama-3.1-8B-Instruct-InWeight-FPGA-WSP — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (masstensor/Llama-3.1-8B-Instruct-InWeight-FPGA-WSP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/masstensor/Llama-3.1-8B-Instruct-InWeight-FPGA-WSP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

Llama-3.1-8B-Instruct-InWeight-OS — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (masstensor/Llama-3.1-8B-Instruct-InWeight-OS). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/masstensor/Llama-3.1-8B-Instruct-InWeight-OS (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

llama-3.2-3b-abliterated — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (lecheyne24/llama-3.2-3b-abliterated). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/lecheyne24/llama-3.2-3b-abliterated (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

Llama-4-Scout-17B-16E-Instruct — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (litert-community/Llama-4-Scout-17B-16E-Instruct). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/litert-community/Llama-4-Scout-17B-16E-Instruct (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

llama3-8b-instruct-med-math-della-k10 — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (ShahriarFerdoush/llama3-8b-instruct-med-math-della-k10). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/ShahriarFerdoush/llama3-8b-instruct-med-math-della-k10 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

llama3-8b-instruct-med-math-pcb-k10 — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (ShahriarFerdoush/llama3-8b-instruct-med-math-pcb-k10). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/ShahriarFerdoush/llama3-8b-instruct-med-math-pcb-k10 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

llm2026-g6-ctrl-legacy-qwen35-08b — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (kanippa/llm2026-g6-ctrl-legacy-qwen35-08b). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/kanippa/llm2026-g6-ctrl-legacy-qwen35-08b (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · mistral · community_reported

mistral-7b-abliterated — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (lecheyne24/mistral-7b-abliterated). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/lecheyne24/mistral-7b-abliterated (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · mistral · community_reported

mistral-nemo-12b-abliterated — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (lecheyne24/mistral-nemo-12b-abliterated). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/lecheyne24/mistral-nemo-12b-abliterated (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Nazo-Qwen3-4B-Thinking-2507 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (nassimjp/Nazo-Qwen3-4B-Thinking-2507). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/nassimjp/Nazo-Qwen3-4B-Thinking-2507 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen-3.8-9B-Uncensored-Heretic-Ch-Enhanced-V1-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Alex500/Qwen-3.8-9B-Uncensored-Heretic-Ch-Enhanced-V1-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Alex500/Qwen-3.8-9B-Uncensored-Heretic-Ch-Enhanced-V1-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen-code-dpo — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (lalit63/qwen-code-dpo). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/lalit63/qwen-code-dpo (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen2.5-3b-abliterated — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (lecheyne24/qwen2.5-3b-abliterated). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/lecheyne24/qwen2.5-3b-abliterated (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen2.5-coder-7b-abliterated — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (lecheyne24/qwen2.5-coder-7b-abliterated). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/lecheyne24/qwen2.5-coder-7b-abliterated (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen3-1.7b-gguf — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (timdedid/qwen3-1.7b-gguf). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/timdedid/qwen3-1.7b-gguf (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3-1.7B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Aguilar82/Qwen3-1.7B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Aguilar82/Qwen3-1.7B-Q4_K_M-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3-30B-A3B-Instruct-2507-NVFP4A16 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (puretensor/Qwen3-30B-A3B-Instruct-2507-NVFP4A16). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/puretensor/Qwen3-30B-A3B-Instruct-2507-NVFP4A16 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3-30B-A3B-Instruct-2507-NVFP4A16-ExpertsOnly — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (puretensor/Qwen3-30B-A3B-Instruct-2507-NVFP4A16-ExpertsOnly). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/puretensor/Qwen3-30B-A3B-Instruct-2507-NVFP4A16-ExpertsOnly (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen3-4b-medQA-kklang — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (dARYNel/qwen3-4b-medQA-kklang). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/dARYNel/qwen3-4b-medQA-kklang (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3-8B-InWeight-FPGA-WSP — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (masstensor/Qwen3-8B-InWeight-FPGA-WSP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/masstensor/Qwen3-8B-InWeight-FPGA-WSP (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3-8B-InWeight-OS — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (masstensor/Qwen3-8B-InWeight-OS). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/masstensor/Qwen3-8B-InWeight-OS (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen3-8b-pmtp — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (Polydim-Einsof/qwen3-8b-pmtp). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Polydim-Einsof/qwen3-8b-pmtp (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen3-cyber-UNCENSORED — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (timdedid/qwen3-cyber-UNCENSORED). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/timdedid/qwen3-cyber-UNCENSORED (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-0.8B-Persian-Agent — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (MohammadBeigi/Qwen3.5-0.8B-Persian-Agent). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/MohammadBeigi/Qwen3.5-0.8B-Persian-Agent (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-0.8B-Persian-Agent-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (MohammadBeigi/Qwen3.5-0.8B-Persian-Agent-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/MohammadBeigi/Qwen3.5-0.8B-Persian-Agent-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-2B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (42ailab/Qwen3.5-2B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/42ailab/Qwen3.5-2B-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-4B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (42ailab/Qwen3.5-4B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/42ailab/Qwen3.5-4B-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-9B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (42ailab/Qwen3.5-9B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/42ailab/Qwen3.5-9B-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-9B-XeFP4 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (KINOQ/Qwen3.5-9B-XeFP4). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/KINOQ/Qwen3.5-9B-XeFP4 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.6-35B-A3B-TR2.25-G-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Ternii/Qwen3.6-35B-A3B-TR2.25-G-GGUF). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/Ternii/Qwen3.6-35B-A3B-TR2.25-G-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-2.4T-A95B — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (Cradia/Qwen3.8-2.4T-A95B). Suitable for private local inference. Hardware: 48GB+ RAM, 42GB disk.

Provenance: https://huggingface.co/Cradia/Qwen3.8-2.4T-A95B (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (42ailab/Qwen3.8-27B-GGUF). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/42ailab/Qwen3.8-27B-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-Hermes-oQ4 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (OnyxAILabs/Qwen3.8-27B-Hermes-oQ4). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/OnyxAILabs/Qwen3.8-27B-Hermes-oQ4 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-NVG-0.55bpw-Experimental-cmf — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (infosave/Qwen3.8-27B-NVG-0.55bpw-Experimental-cmf). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/infosave/Qwen3.8-27B-NVG-0.55bpw-Experimental-cmf (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-pi-adapted-oQ6-bf16-mtp-dflash2-kapitsa — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (jongstra/Qwen3.8-27B-pi-adapted-oQ6-bf16-mtp-dflash2-kapitsa). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/jongstra/Qwen3.8-27B-pi-adapted-oQ6-bf16-mtp-dflash2-kapitsa (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-trellis-2.8bpw-abliterated-ignis — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (gpillon/Qwen3.8-27B-trellis-2.8bpw-abliterated-ignis). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/gpillon/Qwen3.8-27B-trellis-2.8bpw-abliterated-ignis (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-XeFP4 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (KINOQ/Qwen3.8-27B-XeFP4). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/KINOQ/Qwen3.8-27B-XeFP4 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

qwen3.8-cyber-uncensored — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (timdedid/qwen3.8-cyber-uncensored). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/timdedid/qwen3.8-cyber-uncensored (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-Flash-Next-T3a392-Ampere-SM80-46GiB-GPU-Weights — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (sachk0/Qwen3.8-Flash-Next-T3a392-Ampere-SM80-46GiB-GPU-Weights). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/sachk0/Qwen3.8-Flash-Next-T3a392-Ampere-SM80-46GiB-GPU-Weights (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-Flash-Next-TR2.31-G-GGUF — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (Ternii/Qwen3.8-Flash-Next-TR2.31-G-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Ternii/Qwen3.8-Flash-Next-TR2.31-G-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step787 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (thkim0305-SNU/Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step787). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/thkim0305-SNU/Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step787 (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

SFT-Qwen3-0.6B-ALFWorld — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (tommmxsx/SFT-Qwen3-0.6B-ALFWorld). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/tommmxsx/SFT-Qwen3-0.6B-ALFWorld (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

sixthphysics-qwen3.5-9b-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (d4ydy/sixthphysics-qwen3.5-9b-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/d4ydy/sixthphysics-qwen3.5-9b-GGUF (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

smart-home-energy-qwen3-scratch — Local Open-Weight Spec (CC-BY-4.0)

Open-weight release from HuggingFace Hub (Design-Thinking-SLM/smart-home-energy-qwen3-scratch). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Design-Thinking-SLM/smart-home-energy-qwen3-scratch (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

test-save-tiny-random-llama3-smashed-pro — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (pruna-test/test-save-tiny-random-llama3-smashed-pro). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/pruna-test/test-save-tiny-random-llama3-smashed-pro (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · qwen · community_reported

ultron-qwen25-05b-onnx-web — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Mosabbir125/ultron-qwen25-05b-onnx-web). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Mosabbir125/ultron-qwen25-05b-onnx-web (synced 2026-11-21).

Xem chi tiết

2026-11-21 · Model mới & Cục bộ · meta_llama · community_reported

voxtral-mini-3b-text-llama — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (vxltxrllc/voxtral-mini-3b-text-llama). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/vxltxrllc/voxtral-mini-3b-text-llama (synced 2026-11-21).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

DeepSeek-R1-Distill-Qwen-1.5B-SGNE-CC-v2 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Nondual-Observer/DeepSeek-R1-Distill-Qwen-1.5B-SGNE-CC-v2). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Nondual-Observer/DeepSeek-R1-Distill-Qwen-1.5B-SGNE-CC-v2 (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-V4-Flash-0731-MaxQ-v4-64GB-CPU-GGUF — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (Synchopate/DeepSeek-V4-Flash-0731-MaxQ-v4-64GB-CPU-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Synchopate/DeepSeek-V4-Flash-0731-MaxQ-v4-64GB-CPU-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · deepseek · community_reported

DeepSeek-V4-Pro — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (pd584/DeepSeek-V4-Pro). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/pd584/DeepSeek-V4-Pro (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (aaaaygd/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/aaaaygd/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

flexing-v1-based-qwen2.5coder — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (lahyk/flexing-v1-based-qwen2.5coder). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/lahyk/flexing-v1-based-qwen2.5coder (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-3-0.8b-csw — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AletheiaAING/gemma-3-0.8b-csw). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AletheiaAING/gemma-3-0.8b-csw (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-3-1b-csw-best — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AletheiaAING/gemma-3-1b-csw-best). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AletheiaAING/gemma-3-1b-csw-best (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-3-1b-csw-best-pruned — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AletheiaAING/gemma-3-1b-csw-best-pruned). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AletheiaAING/gemma-3-1b-csw-best-pruned (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-3-1b-csw-best-pruned-fp8 — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AletheiaAING/gemma-3-1b-csw-best-pruned-fp8). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AletheiaAING/gemma-3-1b-csw-best-pruned-fp8 (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-3-1b-csw-sft — Local Open-Weight Spec (OTHER)

Open-weight release from HuggingFace Hub (AletheiaAING/gemma-3-1b-csw-sft). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/AletheiaAING/gemma-3-1b-csw-sft (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-4-12B-penguin — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (glyd/gemma-4-12B-penguin). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/glyd/gemma-4-12B-penguin (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-4-12B-wren — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (glyd/gemma-4-12B-wren). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/glyd/gemma-4-12B-wren (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-4-31B-penguin — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (glyd/gemma-4-31B-penguin). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/glyd/gemma-4-31B-penguin (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

gemma-4-31B-wren — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (glyd/gemma-4-31B-wren). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/glyd/gemma-4-31B-wren (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

Gemma-4-E2B-it-ARA-Abliterated-i1-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (mradermacher/Gemma-4-E2B-it-ARA-Abliterated-i1-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/mradermacher/Gemma-4-E2B-it-ARA-Abliterated-i1-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

GPT-Distill-Qwen3-8B-Spellguard-SLERP — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (ITLL/GPT-Distill-Qwen3-8B-Spellguard-SLERP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/ITLL/GPT-Distill-Qwen3-8B-Spellguard-SLERP (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · meta_llama · community_reported

Llama-3.2-3B-Alpaca-ID-GRPO — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (jeffrymahbuubi/Llama-3.2-3B-Alpaca-ID-GRPO). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/jeffrymahbuubi/Llama-3.2-3B-Alpaca-ID-GRPO (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · meta_llama · community_reported

Nous-Hermes-Llama2-13b-Storywriter-GGUF — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (mradermacher/Nous-Hermes-Llama2-13b-Storywriter-GGUF). Suitable for private local inference. Hardware: 16GB+ RAM, 10GB disk.

Provenance: https://huggingface.co/mradermacher/Nous-Hermes-Llama2-13b-Storywriter-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Pakistani_legal_Qwen3b_8b — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Mohsin245/Pakistani_legal_Qwen3b_8b). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Mohsin245/Pakistani_legal_Qwen3b_8b (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · huggingface · community_reported

phi-4-GGUF — Local Open-Weight Spec (MIT)

Open-weight release from HuggingFace Hub (Xylolabs/phi-4-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/phi-4-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Cập nhật Giá xác minh · mistral · provider_reported

Pixtral Large 2502 — Verified Pricing & Capability Record

Input $2/1M · Output $6/1M · Context 128,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen-VL — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (PNG79/Qwen-VL). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/PNG79/Qwen-VL (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

qwen2.5-0.5b-instruct-abliterated — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (LukeFrazier23/qwen2.5-0.5b-instruct-abliterated). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/LukeFrazier23/qwen2.5-0.5b-instruct-abliterated (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-0.6B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (jffernandez26/Qwen3-0.6B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/jffernandez26/Qwen3-0.6B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-0.6B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (S1L53R/Qwen3-0.6B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/S1L53R/Qwen3-0.6B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-0.6B-Q8_0-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (jffernandez26/Qwen3-0.6B-Q8_0-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/jffernandez26/Qwen3-0.6B-Q8_0-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-1.7B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (693448Manu/Qwen3-1.7B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/693448Manu/Qwen3-1.7B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-1.7B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (CarlosVeRu/Qwen3-1.7B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/CarlosVeRu/Qwen3-1.7B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-1.7B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (David0101011/Qwen3-1.7B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/David0101011/Qwen3-1.7B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-1.7B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Frank815/Qwen3-1.7B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Frank815/Qwen3-1.7B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-1.7B-Q8_0-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Frank815/Qwen3-1.7B-Q8_0-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Frank815/Qwen3-1.7B-Q8_0-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-4B-Q4_K_M-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (RafaAlu/Qwen3-4B-Q4_K_M-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/RafaAlu/Qwen3-4B-Q4_K_M-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

qwen3-4b-toolcall-dpo-awq-w4a16 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (arman-52/qwen3-4b-toolcall-dpo-awq-w4a16). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/arman-52/qwen3-4b-toolcall-dpo-awq-w4a16 (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

qwen3-4b-toolcall-dpo-merged — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (arman-52/qwen3-4b-toolcall-dpo-merged). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/arman-52/qwen3-4b-toolcall-dpo-merged (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3-8B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/Qwen3-8B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/Qwen3-8B-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-0.8B — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (litert-community/Qwen3.5-0.8B). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/litert-community/Qwen3.5-0.8B (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

qwen3.5-2b-gym-grpo-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (riccardoroselli/qwen3.5-2b-gym-grpo-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/riccardoroselli/qwen3.5-2b-gym-grpo-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-4B-Base-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/Qwen3.5-4B-Base-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/Qwen3.5-4B-Base-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-4B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/Qwen3.5-4B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/Qwen3.5-4B-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-9B-Base-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/Qwen3.5-9B-Base-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/Qwen3.5-9B-Base-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.5-9B-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (Xylolabs/Qwen3.5-9B-GGUF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Xylolabs/Qwen3.5-9B-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.6-35B-A3B-Fable-5-Distill-heretic-i1-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (mradermacher/Qwen3.6-35B-A3B-Fable-5-Distill-heretic-i1-GGUF). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/mradermacher/Qwen3.6-35B-A3B-Fable-5-Distill-heretic-i1-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (litert-community/Qwen3.8-27B). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/litert-community/Qwen3.8-27B (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (esatapedico/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/esatapedico/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4 (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4-MTP-GGUF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (esatapedico/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4-MTP-GGUF). Suitable for private local inference. Hardware: 24GB+ RAM, 20GB disk.

Provenance: https://huggingface.co/esatapedico/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-NVFP4-MTP-GGUF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Qwen3.8-Flash-Next-3.55BPW-MTP — Local Open-Weight Spec (Open-Weight (check model card))

Open-weight release from HuggingFace Hub (Beling86/Qwen3.8-Flash-Next-3.55BPW-MTP). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/Beling86/Qwen3.8-Flash-Next-3.55BPW-MTP (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

QwenPU-RF — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (pratx1/QwenPU-RF). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/pratx1/QwenPU-RF (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

redline-bank-qwen3-0.6b — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (ahmedoussama/redline-bank-qwen3-0.6b). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/ahmedoussama/redline-bank-qwen3-0.6b (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step760 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (thkim0305-SNU/Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step760). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/thkim0305-SNU/Safety_Tuning-Qwen3.5-4B-Base-GRPO-Mixture8-binary-lr1e-6-kl0.001-p15-k8-step760 (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

tech-challenge-gemma-llm-fine-tuning-light — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (ramoncg/tech-challenge-gemma-llm-fine-tuning-light). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/ramoncg/tech-challenge-gemma-llm-fine-tuning-light (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · google_gemini · community_reported

tech-challenge-gemma-llm-fine-tuning-light-v6 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (ramoncg/tech-challenge-gemma-llm-fine-tuning-light-v6). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/ramoncg/tech-challenge-gemma-llm-fine-tuning-light-v6 (synced 2026-11-20).

Xem chi tiết

2026-11-20 · Model mới & Cục bộ · qwen · community_reported

Tenet-8B-Qwen3-Unslop-v2 — Local Open-Weight Spec (APACHE-2.0)

Open-weight release from HuggingFace Hub (mr-andrey-isachenko/Tenet-8B-Qwen3-Unslop-v2). Suitable for private local inference. Hardware: 8GB+ RAM, 5.5GB disk.

Provenance: https://huggingface.co/mr-andrey-isachenko/Tenet-8B-Qwen3-Unslop-v2 (synced 2026-11-20).

Xem chi tiết

2026-11-19 · Hướng dẫn & So sánh · agentpilot_editorial · published

Claude Sonnet 4.5 vs GPT-4.1: Coding, Context & Cost Comparison

Side-by-side comparison of verified API pricing, context limits, reasoning support, and workflow fit between Anthropic Claude Sonnet 4.5 and OpenAI GPT-4.1.

Backed by live catalog records anthropic/claude-sonnet-4-5 & openai/gpt-4.1.

Xem chi tiết

2026-11-19 · Hướng dẫn & So sánh · agentpilot_editorial · published

DeepSeek R1 vs OpenAI o3: Reasoning Cost & Trade-Offs

Compare DeepSeek R1 and OpenAI o3 for complex debugging, architecture review, and cost-controlled reasoning tasks using verified catalog pricing.

Backed by live catalog records deepseek/deepseek-reasoner-r1 & openai/o3.

Xem chi tiết

2026-11-19 · Hướng dẫn & So sánh · agentpilot_editorial · published

DeepSeek V3 vs Mistral Codestral 25.01: Pricing, Coding & Context

Compare DeepSeek V3 and Mistral Codestral 25.01 across verified token pricing, coding scores, structured output, and regional workflow preferences.

Backed by live catalog records deepseek/deepseek-chat-v3 & mistral/codestral-2501.

Xem chi tiết

2026-11-19 · Hướng dẫn & So sánh · agentpilot_editorial · published

Gemini 2.5 Pro vs Claude Sonnet 4.5: Long Context & Multimodal Workflows

Evaluate Google Gemini 2.5 Pro against Anthropic Claude Sonnet 4.5 across context window capacity, audio/video/PDF inputs, verified pricing, and agent client support.

Backed by live catalog records google_gemini/gemini-2.5-pro & anthropic/claude-sonnet-4-5.

Xem chi tiết

2026-11-19 · Hướng dẫn & So sánh · agentpilot_editorial · published

GPT-4.1 mini vs Gemini 2.5 Flash: Economy Profile Comparison

Compare two fast, low-cost cloud models for routine coding, content workflows, SEO checks, and high-frequency agent steps under strict budgets.

Backed by live catalog records openai/gpt-4.1-mini & google_gemini/gemini-2.5-flash.

Xem chi tiết

2026-11-19 · Hướng dẫn & So sánh · agentpilot_editorial · published

Qwen 2.5 Coder 32B (Ollama) vs Llama 3.3 70B: Local Hardware & Privacy Comparison

Compare RAM, VRAM, disk footprint, licensing, and coding specialization for teams running private offline workflows without cloud inference fees.

Backed by live catalog records qwen/qwen2.5-coder-32b-local & meta_llama/llama-3.3-70b-instruct.

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · openai · curated

Accessible React Dashboard + Technical SEO Metadata

WCAG-compliant React and Tailwind interface paired with clean OpenGraph metadata, canonical URLs, and structured data validation. Expected cost: $0.4608 (Single-Agent).

Deterministically generated from AgentPilot planner (balanced profile).

Xem chi tiết

2026-11-18 · Hướng dẫn & So sánh · agentpilot_editorial · published

Auditing Open Agent Skills (SKILL.md) Before Local Installation

How to inspect SKILL.md instructions, SHA-256 checksums, path traversal defenses, executable scripts, and prompt-injection risks before trusting any third-party skill.

Localized in EN, VI, ZH-CN · 6 min read.

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · openai · curated

Budget-Capped API Automated Testing & QA Suite

Low-cost single-agent setup for generating deterministic unit, contract, and regression tests for an existing Node.js REST service. Expected cost: $0.0538 (Single-Agent).

Deterministically generated from AgentPilot planner (economy profile).

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · openai · curated

CI/CD Pipeline Automation & Release Runbook

Automate repository linting, security scanning, and zero-downtime deployment checklists with portable Open Agent Skills. Expected cost: $0.5764 (Single-Agent).

Deterministically generated from AgentPilot planner (balanced profile).

Xem chi tiết

2026-11-18 · Hướng dẫn & So sánh · agentpilot_editorial · published

Designing a Reproducible Coding Agent Setup Across Claude Code, Codex & Cursor

How portable Open Agent Skills (.agents/skills) and client-specific paths keep team instructions, model profiles, and security checks reproducible.

Localized in EN, VI, ZH-CN · 5 min read.

Xem chi tiết

2026-11-18 · Hướng dẫn & So sánh · agentpilot_editorial · published

Estimating AI Workflow Token Consumption & Cost Ranges Transparently

Why single-number AI cost promises mislead teams, and how to model planner tokens, execution turns, context handoffs, retries, and cached input discounts.

Localized in EN, VI, ZH-CN · 5 min read.

Xem chi tiết

2026-11-18 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini 4 Neon — Verified Pricing & Capability Record

Input $3/1M · Output $15/1M · Cached $0.15/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-18).

Xem chi tiết

2026-11-18 · Hướng dẫn & So sánh · agentpilot_editorial · published

How to Choose an AI Model Without Guessing: Capabilities, Context & Pricing Provenance

Stop picking models by hype. Learn how to match task capabilities, context windows, tool calling, and verified pricing tiers to your real workload.

Localized in EN, VI, ZH-CN · 5 min read.

Xem chi tiết

2026-11-18 · Hướng dẫn & So sánh · agentpilot_editorial · published

Local Open-Weight Models vs Cloud APIs: Hardware Reality & Privacy Trade-Offs

Understand RAM, VRAM, quantization, disk footprint, and when a local Ollama model beats a cloud API—and when it does not.

Localized in EN, VI, ZH-CN · 5 min read.

Xem chi tiết

2026-11-18 · Cập nhật Giá xác minh · huggingface · unknown

Mistral Small 3 24B (Community Preview) — Verified Pricing & Capability Record

Apache-2.0 open-weight model hosted across community inference endpoints with unverified hosted pricing. Pricing currently listed as unknown (not fabricated).

Provenance: Unverified — hosted API pricing not published by source (synced 2026-11-18).

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · google_gemini · curated

Multilingual Technical SEO & Content Architecture

Audit hreflang tags, XML sitemaps, canonical hygiene, and internal link graphs for a multi-locale documentation website. Expected cost: $0.0813 (Single-Agent).

Deterministically generated from AgentPilot planner (economy profile).

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · qwen · curated

Offline Local Python Data Analysis & Refactoring

Zero-cloud-egress local refactoring of an internal Python CSV profiling and analytics pipeline using open-weight Ollama weights. Expected cost: $0.0000 (Single-Agent).

Deterministically generated from AgentPilot planner (balanced profile).

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · google_gemini · curated

OpenAPI Reference & Developer Documentation Pack

Generate clear, accurate endpoint guides, migration notes, and curl examples directly from TypeScript route handlers. Expected cost: $0.1247 (Single-Agent).

Deterministically generated from AgentPilot planner (economy profile).

Xem chi tiết

2026-11-18 · Hướng dẫn & So sánh · agentpilot_editorial · published

Single-Agent vs Multi-Agent Workflows: When Simplicity Beats Complexity

A practical engineering framework for deciding between a single well-equipped agent and a multi-agent DAG without wasting context handoff tokens.

Localized in EN, VI, ZH-CN · 6 min read.

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · anthropic · curated

Structured Market & Competitive Research Synthesis

Single-agent long-context research workflow synthesizing public technical specs, pricing tiers, and citation-backed summaries. Expected cost: $0.4357 (Single-Agent).

Deterministically generated from AgentPilot planner (quality profile).

Xem chi tiết

2026-11-18 · Workflow tuyển chọn · openai · curated

TypeScript Billing API + SQL Migrations & OWASP Audit

Production-grade Next.js billing API with PostgreSQL schema migrations, automated test coverage, and an independent OWASP security review. Expected cost: $1.0126 (Multi-Agent).

Deterministically generated from AgentPilot planner (balanced profile).

Xem chi tiết

2026-11-17 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.2 Astra — Verified Pricing & Capability Record

Input $8/1M · Output $40/1M · Cached $0.4/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-17).

Xem chi tiết

2026-11-17 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.2 Astra Pro — Verified Pricing & Capability Record

Input $8/1M · Output $40/1M · Cached $0.4/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-17).

Xem chi tiết

2026-11-17 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.2 Sol — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-17).

Xem chi tiết

2026-11-17 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.2 Sol Pro — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-17).

Xem chi tiết

2026-11-16 · Cập nhật Giá xác minh · qwen · provider_reported

Qwen4 Max — Verified Pricing & Capability Record

Input $1.425/1M · Output $4.275/1M · Cached $0.0713/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-16).

Xem chi tiết

2026-11-15 · Skill đã xác minh · github.com/agentskills/agentskills · Verified Source

OWASP Application Security Audit (v2.0.0) — Verified Source

Performs threat modeling, secret scanning, auth/RBAC boundary audits, and injection/path-traversal review. Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 003a1b9ee6960eb4… · Category: Security.

Xem chi tiết

2026-11-15 · Model mới & Cục bộ · qwen · verified

Qwen 2.5 Coder 32B (Local) — Local Open-Weight Spec (Apache-2.0)

Apache-2.0 open-weight local coding specialist runnable offline via Ollama or LM Studio with zero API fees. Hardware: 24GB+ RAM, 20GB disk.

Provenance: Local open-weight execution (hardware electricity only; $0 API fee) (synced 2026-11-15).

Xem chi tiết

2026-11-15 · Model mới & Cục bộ · ollama · verified

Qwen 2.5 Coder 7B (Laptop Local) — Local Open-Weight Spec (Apache-2.0)

Compact local coding model designed for 16GB RAM developer laptops with zero cloud data transfer. Hardware: 8GB+ RAM, 5GB disk.

Provenance: Local open-weight execution ($0 API fee) (synced 2026-11-15).

Xem chi tiết

2026-11-14 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

Accessible React & Tailwind UI (v2.1.0) — Verified Source

Structured frontend patterns for responsive layouts, keyboard accessibility, WCAG contrast, and semantic HTML components. Compatible with claude_code, cursor, gemini_cli, opencode, agent_skills_generic.

SHA-256 5c2485a3112fef3a… · Category: Frontend Development.

Xem chi tiết

2026-11-14 · Cập nhật Giá xác minh · google_gemini · verified

Gemini 2.5 Flash — Verified Pricing & Capability Record

Input $0.3/1M · Output $2.5/1M · Cached $0.075/1M · Context 1,048,576 tokens.

Provenance: https://ai.google.dev/gemini-api/docs/pricing (synced 2026-11-14).

Xem chi tiết

2026-11-14 · Cập nhật Giá xác minh · google_gemini · verified

Gemini 2.5 Pro — Verified Pricing & Capability Record

Input $1.25/1M · Output $10/1M · Cached $0.31/1M · Context 1,048,576 tokens.

Provenance: https://ai.google.dev/gemini-api/docs/pricing (synced 2026-11-14).

Xem chi tiết

2026-11-13 · Skill đã xác minh · github.com/microsoft/agent-skills · Verified Source

Automated Testing & QA Harness (v1.6.1) — Verified Source

Builds deterministic unit tests, contract tests, regression suites, and Playwright browser verification journeys. Compatible with github_copilot, claude_code, openai_codex, cursor, gemini_cli, agent_skills_generic.

SHA-256 acaa7e28d3bb7a05… · Category: Testing & QA.

Xem chi tiết

2026-11-13 · Skill đã xác minh · github.com/agentskills/agentskills · Verified Source

Docker, CI/CD & Release Hardening (v1.2.4) — Verified Source

Creates reproducible multi-stage Dockerfiles, GitHub Actions pipelines, and deployment health checks. Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 deb6fa5ba0150d9d… · Category: DevOps.

Xem chi tiết

2026-11-12 · Skill đã xác minh · github.com/microsoft/agent-skills · Verified Source

Architecture & API Documentation (v1.4.2) — Verified Source

Generates OpenAPI specs, ADRs, runbooks, and developer onboarding documentation aligned with live code. Compatible with github_copilot, claude_code, openai_codex, cursor, gemini_cli, opencode, agent_skills_generic.

SHA-256 0fc648b3fff9d253… · Category: Documentation.

Xem chi tiết

2026-11-12 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini 4 Hydrogen — Verified Pricing & Capability Record

Input $1.5/1M · Output $7.5/1M · Cached $0.075/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-12).

Xem chi tiết

2026-11-12 · Cập nhật Giá xác minh · openai · verified

GPT-4.1 — Verified Pricing & Capability Record

Input $2/1M · Output $8/1M · Cached $0.5/1M · Context 1,047,576 tokens.

Provenance: https://openai.com/api/pricing/ (synced 2026-11-12).

Xem chi tiết

2026-11-12 · Cập nhật Giá xác minh · openai · verified

GPT-4.1 mini — Verified Pricing & Capability Record

Input $0.4/1M · Output $1.6/1M · Cached $0.1/1M · Context 1,047,576 tokens.

Provenance: https://openai.com/api/pricing/ (synced 2026-11-12).

Xem chi tiết

2026-11-12 · Skill mới · github.com/google/agent-skills · Warning

Local Data Analysis & Statistical Profiling (v1.5.0) — Warning

Analyzes CSV, Parquet, and SQLite datasets locally with Python scripts, summary statistics, and anomaly checks. Compatible with gemini_cli, claude_code, openai_codex, cursor, opencode.

SHA-256 3d3425809091b5d9… · Category: Data Analysis.

Xem chi tiết

2026-11-12 · Cập nhật Giá xác minh · openai · verified

OpenAI o3 — Verified Pricing & Capability Record

Input $2/1M · Output $8/1M · Cached $0.5/1M · Context 200,000 tokens.

Provenance: https://openai.com/api/pricing/ (synced 2026-11-12).

Xem chi tiết

2026-11-12 · Cập nhật Giá xác minh · openai · verified

Text Embedding 3 Large — Verified Pricing & Capability Record

Input $0.13/1M · Output $0/1M · Context 8,191 tokens.

Provenance: https://openai.com/api/pricing/ (synced 2026-11-12).

Xem chi tiết

2026-11-12 · Skill đã xác minh · github.com/agentskills/agentskills · Verified Source

TypeScript Full-Stack Architecture (v1.4.0) — Verified Source

Guides strict TypeScript module design, clean API contracts, and incremental refactoring across Next.js and Node services. Compatible with claude_code, openai_codex, cursor, github_copilot, gemini_cli, opencode, agent_skills_generic.

SHA-256 8b3427b4ef93b0a0… · Category: Software Development.

Xem chi tiết

2026-11-11 · Skill đã xác minh · github.com/openai/skills · Verified Source

Backend API & Contract Engineering (v1.3.2) — Verified Source

Designs idempotent REST and RPC endpoints, input schema validation, rate limiting, and structured error envelopes. Compatible with openai_codex, claude_code, cursor, github_copilot, gemini_cli, agent_skills_generic.

SHA-256 27f31d3a087ed33b… · Category: Backend Development.

Xem chi tiết

2026-11-11 · Skill mới · github.com/openai/skills · Warning

Local CLI & Task Automation (v1.1.2) — Warning

Creates idempotent build scripts, git hooks, and reproducible local task runners with dry-run support. Compatible with openai_codex, claude_code, gemini_cli, opencode.

SHA-256 345398aa0403fffe… · Category: Automation.

Xem chi tiết

2026-11-10 · Cập nhật Giá xác minh · anthropic · verified

Claude 3.5 Haiku — Verified Pricing & Capability Record

Input $0.8/1M · Output $4/1M · Cached $0.08/1M · Context 200,000 tokens.

Provenance: https://docs.anthropic.com/en/docs/about-claude/models/overview (synced 2026-11-10).

Xem chi tiết

2026-11-10 · Cập nhật Giá xác minh · anthropic · verified

Claude Sonnet 4.5 — Verified Pricing & Capability Record

Input $3/1M · Output $15/1M · Cached $0.3/1M · Context 200,000 tokens.

Provenance: https://docs.anthropic.com/en/docs/about-claude/models/overview (synced 2026-11-10).

Xem chi tiết

2026-11-10 · Skill đã xác minh · skills.sh/official/design-system-tokens · Verified Source

Design Systems & Visual Hierarchy (v1.3.0) — Verified Source

Establishes typographic scales, spacing tokens, accessible color palettes, and component layout specifications. Compatible with claude_code, cursor, gemini_cli, agent_skills_generic.

SHA-256 8ccf268644b1eb54… · Category: Design.

Xem chi tiết

2026-11-10 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini 4 Carbon — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-10).

Xem chi tiết

2026-11-10 · Cập nhật Giá xác minh · meta_llama · community_reported

Llama 3.3 70B Instruct — Verified Pricing & Capability Record

Input $0/1M · Output $0/1M · Cached $0/1M · Context 131,072 tokens.

Provenance: Local open-weight execution ($0 API fee); hosted pricing varies by provider (synced 2026-11-10).

Xem chi tiết

2026-11-10 · Skill đã xác minh · github.com/google/agent-skills · Verified Source

SQLite & PostgreSQL Schema Migrations (v1.2.0) — Verified Source

Safe zero-downtime schema evolution, index tuning, transactional migrations, and rollback scripts for SQL databases. Compatible with gemini_cli, claude_code, openai_codex, cursor, opencode, agent_skills_generic.

SHA-256 8b9584d2f429c2cd… · Category: Database.

Xem chi tiết

2026-11-09 · Cập nhật Giá xác minh · anthropic · provider_reported

Claude Fable 5.2 — Verified Pricing & Capability Record

Input $8/1M · Output $40/1M · Cached $0.2/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-09).

Xem chi tiết

2026-11-09 · Skill đã xác minh · github.com/anthropics/skills · Verified Source

Source-Verified Technical Research (v1.0.4) — Verified Source

Synthesizes technical papers, vendor documentation, and trade-off matrices with strict citation discipline. Compatible with claude_code, gemini_cli, cursor, agent_skills_generic.

SHA-256 f916a72529fc9751… · Category: Research.

Xem chi tiết

2026-11-08 · Skill đã xác minh · skills.sh/official/technical-seo-audit · Verified Source

Technical SEO & Structured Data (v1.1.0) — Verified Source

Audits crawlability, canonical tags, OpenGraph metadata, Core Web Vitals, and Schema.org JSON-LD markup. Compatible with claude_code, cursor, gemini_cli, agent_skills_generic.

SHA-256 6c1c539322741722… · Category: SEO.

Xem chi tiết

2026-11-06 · Skill đã xác minh · skills.sh/official/editorial-content-studio · Verified Source

Technical Editorial & Release Writing (v1.2.1) — Verified Source

Produces clear release notes, developer blog posts, launch guides, and concise product copy without marketing fluff. Compatible with claude_code, openai_codex, cursor, gemini_cli, agent_skills_generic.

SHA-256 65a4a2d9571b424d… · Category: Content Creation.

Xem chi tiết

2026-11-05 · Cập nhật Giá xác minh · deepseek · provider_reported

DeepSeek-R1 — Verified Pricing & Capability Record

Input $0.55/1M · Output $2.19/1M · Cached $0.14/1M · Context 128,000 tokens.

Provenance: https://api-docs.deepseek.com/quick_start/pricing (synced 2026-11-05).

Xem chi tiết

2026-11-05 · Cập nhật Giá xác minh · deepseek · provider_reported

DeepSeek-V3 — Verified Pricing & Capability Record

Input $0.27/1M · Output $1.1/1M · Cached $0.07/1M · Context 128,000 tokens.

Provenance: https://api-docs.deepseek.com/quick_start/pricing (synced 2026-11-05).

Xem chi tiết

2026-11-05 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini Omni 1.2 Flash — Verified Pricing & Capability Record

Input $1.5/1M · Output $9/1M · Context 131,072 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-05).

Xem chi tiết

2026-11-04 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini Omni 1.1 Flash — Verified Pricing & Capability Record

Input $1.5/1M · Output $9/1M · Context 131,072 tokens.

Provenance: https://openrouter.ai/models (synced 2026-11-04).

Xem chi tiết

2026-11-04 · Skill đã xác minh · github.com/open-biz-skills/product-pricing-modeler · Static Scan Passed

SaaS Unit Economics & Business Modeling (v0.9.4) — Static Scan Passed

Models unit economics, pricing tiers, sensitivity analysis, and executive decision memos from structured inputs. Compatible with claude_code, cursor, gemini_cli, agent_skills_generic.

SHA-256 14da6ff37daf2e2b… · Category: Business.

Xem chi tiết

2026-11-02 · Skill đã xác minh · github.com/community-cursor/cursor-only-ui-macros · Static Scan Passed

Cursor Rule & Workspace Macros (v0.8.1) — Static Scan Passed

Community Cursor-specific rule templates for rapid React refactoring (Cursor client only; incompatible with other clients). Compatible with cursor.

SHA-256 d6d1ba693ff838cc… · Category: Frontend Development.

Xem chi tiết

2026-10-28 · Cập nhật Giá xác minh · xai · provider_reported

Grok 3 — Verified Pricing & Capability Record

Input $3/1M · Output $15/1M · Context 131,072 tokens.

Provenance: https://docs.x.ai/docs/models (synced 2026-10-28).

Xem chi tiết

2026-10-26 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.1 Terra — Verified Pricing & Capability Record

Input $1/1M · Output $5/1M · Cached $0.05/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-26).

Xem chi tiết

2026-10-26 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.1 Terra Pro — Verified Pricing & Capability Record

Input $1/1M · Output $5/1M · Cached $0.05/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-26).

Xem chi tiết

2026-10-20 · Cập nhật Giá xác minh · mistral · provider_reported

Codestral 25.01 — Verified Pricing & Capability Record

Input $0.3/1M · Output $0.9/1M · Context 256,000 tokens.

Provenance: https://mistral.ai/pricing (synced 2026-10-20).

Xem chi tiết

2026-10-17 · Cập nhật Giá xác minh · deepseek · provider_reported

DeepSeek V4.1 Flash 1017 — Verified Pricing & Capability Record

Input $0.15/1M · Output $0.6/1M · Cached $0.003/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-17).

Xem chi tiết

2026-10-13 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini 4 Argon — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-13).

Xem chi tiết

2026-10-07 · Cập nhật Giá xác minh · anthropic · provider_reported

Claude Haiku 5.5 — Verified Pricing & Capability Record

Input $0.1/1M · Output $0.5/1M · Cached $0.01/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-07).

Xem chi tiết

2026-10-06 · Cập nhật Giá xác minh · mistral · provider_reported

Mistral Large 4 — Verified Pricing & Capability Record

Input $0.7/1M · Output $2.1/1M · Cached $0.07/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-06).

Xem chi tiết

2026-10-06 · Cập nhật Giá xác minh · google_gemini · provider_reported

Nano Banana 2.1 — Verified Pricing & Capability Record

Input $1.5/1M · Output $7.5/1M · Context 65,536 tokens.

Provenance: https://openrouter.ai/models (synced 2026-10-06).

Xem chi tiết

2026-09-29 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.1 Sol — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-29).

Xem chi tiết

2026-09-29 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6.1 Sol Pro — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-29).

Xem chi tiết

2026-09-28 · Cập nhật Giá xác minh · anthropic · provider_reported

Claude Sonnet 5.5 — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.1/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-28).

Xem chi tiết

2026-09-23 · Cập nhật Giá xác minh · qwen · provider_reported

Qwen3.8 Max Prime — Verified Pricing & Capability Record

Input $4/1M · Output $12/1M · Cached $0.5/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-23).

Xem chi tiết

2026-09-22 · Cập nhật Giá xác minh · anthropic · provider_reported

Claude Opus 5.5 — Verified Pricing & Capability Record

Input $4/1M · Output $20/1M · Cached $0.2/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-22).

Xem chi tiết

2026-09-22 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6 Luna — Verified Pricing & Capability Record

Input $0.1/1M · Output $0.5/1M · Cached $0.01/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-22).

Xem chi tiết

2026-09-22 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6 Luna Pro — Verified Pricing & Capability Record

Input $0.1/1M · Output $0.5/1M · Cached $0.01/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-22).

Xem chi tiết

2026-09-22 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6 Sol — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.2/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-22).

Xem chi tiết

2026-09-22 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6 Sol Pro — Verified Pricing & Capability Record

Input $2/1M · Output $10/1M · Cached $0.2/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-22).

Xem chi tiết

2026-09-21 · Cập nhật Giá xác minh · xai · provider_reported

Grok 4.7 — Verified Pricing & Capability Record

Input $2/1M · Output $6/1M · Cached $0.5/1M · Context 500,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-21).

Xem chi tiết

2026-09-21 · Cập nhật Giá xác minh · qwen · provider_reported

Qwen3.8 Omni Flash — Verified Pricing & Capability Record

Input $0.15/1M · Output $0.47/1M · Cached $0.016/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-21).

Xem chi tiết

2026-09-10 · Cập nhật Giá xác minh · deepseek · provider_reported

DeepSeek V4.1 Flash — Verified Pricing & Capability Record

Input $0.0498/1M · Output $0.1992/1M · Cached $0.001/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-10).

Xem chi tiết

2026-09-04 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6 Astra — Verified Pricing & Capability Record

Input $10/1M · Output $50/1M · Cached $1/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-04).

Xem chi tiết

2026-09-04 · Cập nhật Giá xác minh · openai · provider_reported

GPT-6 Astra Pro — Verified Pricing & Capability Record

Input $10/1M · Output $50/1M · Cached $1/1M · Context 1,050,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-04).

Xem chi tiết

2026-09-03 · Cập nhật Giá xác minh · qwen · provider_reported

Qwen3.8 Max (0902) — Verified Pricing & Capability Record

Input $2/1M · Output $6/1M · Cached $0.25/1M · Context 1,000,000 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-03).

Xem chi tiết

2026-09-02 · Cập nhật Giá xác minh · google_gemini · provider_reported

Gemini 3.8 Flash — Verified Pricing & Capability Record

Input $0.825/1M · Output $4.125/1M · Cached $0.0825/1M · Context 1,048,576 tokens.

Provenance: https://openrouter.ai/models (synced 2026-09-02).

Xem chi tiết

2026-08-01 · Cập nhật Giá xác minh · alibaba_cloud · provider_reported

Qwen Max (Model Studio) — Verified Pricing & Capability Record

Input $1.6/1M · Output $6.4/1M · Context 131,072 tokens.

Provenance: https://www.alibabacloud.com/help/en/model-studio/models (synced 2026-08-01).

Xem chi tiết

2026-06-01 · Tương thích & Ngừng hỗ trợ · anthropic · deprecated

Claude 2.1 (Retired) — Deprecation & Replacement Record

Input $8/1M · Output $24/1M · Context 200,000 tokens.

Provenance: https://docs.anthropic.com/en/docs/resources/model-deprecations (synced 2026-06-01).

Xem chi tiết

2026-06-01 · Tương thích & Ngừng hỗ trợ · openai · deprecated

GPT-4 (0314 Legacy) — Deprecation & Replacement Record

Input $30/1M · Output $60/1M · Context 8,192 tokens.

Provenance: https://platform.openai.com/docs/deprecations (synced 2026-06-01).

Xem chi tiết
Catalog Updates & Model Changelog | PlanMyAI (Tiếng Việt)