Ollama
OPEN SOURCERun LLaMA, Mistral, Gemma, and 100+ LLMs locally with a single command.
Free
About
Ollama makes it simple to run large language models locally on Mac, Linux, and Windows. Pull any model with one command, serve it through an OpenAI-compatible REST API, and use GPU acceleration for fast inference — all completely free.
Features
100+ models: LLaMA, Mistral, Gemma, Qwen
One-command model pull & run
OpenAI-compatible REST API
GPU & CPU acceleration
Multi-model management
Cross-platform: Mac, Linux, Windows
Specifications
| Context Window | Model dependent |
| Tool Use | |
| Vision | |
| Streaming | |
| Open Source | |
| Self-Host | |
| Starting Price | Free |
Community Feedback
Quick Info
Free
Download Free