24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
911.8K Pulls 6 Tags Updated 7 months ago
123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
258.7K Pulls 5 Tags Updated 7 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.
992.5K 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.
963.3K Pulls 33 Tags Updated 1 year ago
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
68.3K Pulls 5 Tags Updated 1 month ago
Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.
1.3M Pulls 17 Tags Updated 8 months ago
14 Pulls 1 Tag Updated 1 month ago
9 Pulls 1 Tag Updated 1 month 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
Agentic coding model for 24 GB GPUs: TeichAI's Gemma-4-31B Fable-5 agent distill (vision + thinking + tools) with a disciplined coding-agent system prompt baked in. Inspect → reproduce → smallest fix → re-verify.
7 Pulls 1 Tag Updated yesterday
Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. It requires bigger value for num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of official qat of gemma4-26b
6 Pulls 1 Tag Updated 5 days ago
Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of https://ollama.com/library/gemma3:1b.
2 Pulls 1 Tag Updated 3 days ago
v2 is built for coding + agentic work — writing code, running commands, using tools, debugging, multi-step technical tasks.
3,108 Pulls 5 Tags Updated 1 month ago
38 Pulls 1 Tag Updated 2 weeks ago
Fixes the issue with Open WebUI not passing tools (native) and system prompt information properly. It requires bigger value for num_ctx default: 32768. Tested with Open WebUI v0.9.6 and v0.10.2. Just built on top of https://ollama.com/library/gemma4:26b.
26 Pulls 1 Tag Updated 1 week ago
Nous Hermes 4.3 36B parameters with thinking and tools enabled
1,108 Pulls 2 Tags Updated 2 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
479 Pulls 1 Tag Updated 3 months ago
Nanbeige4.1-3B-q4_K_M no think tools fit 4G-6G GPU OpenClaw local free tokens LobsterAI
407 Pulls 1 Tag Updated 4 months ago
A quick fix for tools and prompts for Qwen3.5 that worked for me :D
340 Pulls 1 Tag Updated 4 months ago
Hermes 4.3 36B (Q8_0) with the correct Llama-3 template — verified tools + thinking capabilities for agent use.
170 Pulls 1 Tag Updated 1 month ago