24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
945.8K Pulls 6 Tags Updated 8 months ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
352.1K Pulls 5 Tags Updated 8 months ago
The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.
1M Pulls 33 Tags Updated 1 year ago
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
984.6K Pulls 33 Tags Updated 2 years ago
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
120.2K Pulls 5 Tags Updated 2 months ago
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
1.4M Pulls 17 Tags Updated 9 months ago
34 Pulls 1 Tag Updated 2 months ago
11 Pulls 1 Tag Updated 2 months ago
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
3.7M Pulls 9 Tags Updated 1 year ago
Zen — a neutral, specialized AI assistant created by Distendo. Built for coding, tools, and research.
3,134 Pulls 1 Tag Updated 3 weeks ago
To run DeepSeek-V4-Flash in full precision lossless, run Q4 (UD-Q4_K_XL), It is 155GB. vision tools thinking
592 Pulls 1 Tag Updated 3 weeks ago
To run DeepSeek-V4-Flash in full precision lossless, run IQ1 (UD-IQ1_S), It is 82GB. vision tools thinking
200 Pulls 1 Tag Updated 3 weeks ago
To run DeepSeek-V4-Flash in full precision lossless, run Q3 (UD-Q3_K_M), It is 129 GB. vision tools thinking
71 Pulls 1 Tag Updated 3 weeks ago
Tiny 152M LLM with chat, step-by-step thinking, tools/web and honest code answers runs on almost anything.
67 Pulls 5 Tags Updated 3 weeks ago
v2 is built for coding + agentic work — writing code, running commands, using tools, debugging, multi-step technical tasks.
3,710 Pulls 5 Tags Updated 2 months ago
Nous Hermes 4.3 36B parameters with thinking and tools enabled
1,666 Pulls 2 Tags Updated 3 months ago
一个可以在A5000显卡或4090上完整运行的QWen3.5大模型（上下文64k），具备调用工具的能力，适合本地部署龙虾和Hermes
576 Pulls 1 Tag Updated 4 months ago
Nanbeige4.1-3B-q4_K_M no think tools fit 4G-6G GPU OpenClaw local free tokens LobsterAI
453 Pulls 1 Tag Updated 5 months ago
Hermes 4.3 36B (Q8_0) with the correct Llama-3 template — verified tools + thinking capabilities for agent use.
261 Pulls 1 Tag Updated 2 months ago
9 Pulls 1 Tag Updated 1 week ago