Ollama makes it trivial to download and run open models such as Llama, Mistral, Gemma and Qwen on your own machine. It exposes a local HTTP API that any app โ including this hub โ can talk to.
One-command local model install
OpenAI-compatible local API
Full offline privacy โ no data leaves your device
Model quantisation for consumer GPUs
Powered by: Llama 3.3 70b, Gemma 3 27b, GPT oss 20b, Mistral Medium 3.1
Open source
Free
Only your own hardware cost
Content based on publicly available data. Verify with the official website.