About
Run and manage open-source LLMs locally on your machine. Supports models like Llama, Mistral, Phi, Gemma, and hundreds more. CLI-first with REST API for integration.
Features
- One-command model pull and run (e.g., 'ollama run llama3').
- Custom Modelfiles for tailoring parameters, prompts, and templates.
- RESTful API for programmatic access and integration into apps.
- Automatic GPU detection and acceleration (CUDA, ROCm, Metal).
- Lightweight Docker-ready deployment for server or local use.
Links
Categories
Reviews
4.7
Write a Review
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.
Related Tools
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.