Run Llama 3, Mistral, Gemma, and other models locally on your machine. No API keys, no cloud dependency — just you and your GPU.
Simple. Local. Open source. The way AI should be.
One command to download and run any supported model. No configuration files, no complex setup.
Your data never leaves your machine. Complete privacy and control over model inference.
Create custom models from a simple config file. Import GGUF, set parameters, define system prompts.
Compatible with OpenAI's API format. Drop-in replacement for existing integrations and tools.
No pricing tiers. No subscriptions. Just free & open source software.
forever. MIT license.
run it anywhere
community powered