ollama

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

171.8k stars16.2k forks970 watchers2359 open issuesGoMIT

EDITOR'S TAKE

Run open-source LLMs locally with one command. ~95k stars. Essential for AI development — test prompts against Llama, Mistral, Phi without burning API credits. Production use is limited unless you have the GPUs.

Use this if

You want to develop and test LLM features without API costs, or run small models on a workstation.

Skip if

You need production inference at scale — use vLLM or a hosted API.