ollama
https://github.com/ollama/ollama
Go
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Go not yet supported6 Subscribers
Add a CodeTriage badge to ollama
Help out
- Issues
- x/create: preserve MLX quantization metadata for prequantized imports
- parser: count a CRLF as one line ending, not two
- Add Ollama-Manager project link to README
- Add vibe-coder to the list of tools
- docs: add protoAgent to Terminal & CLI integrations
- Recover qwen3-coder tool calls that omit the <tool_call> wrapper
- PARAMETER temperature from the Modelfile is ignored on /v1/chat/completions but honoured on /api/chat
- /api/chat silently drops `audios` on audio-capable models (gemma4:e4b) instead of erroring
- CUDA illegal memory access in launch_mul_mat_q on qwen3.6:35b during prefill - prompt-size dependent, regression between 0.31.2 and 0.32.9
- GLM 5.3
- Docs
- Go not yet supported