Run LLMs locally — Llama, Mistral, Gemma, DeepSeek, and 100+ models via CLI and REST API. OpenAI-compatible endpoint at localhost:11434 for direct agent integration.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- OpenAI-Compatible API
Use Ollama to call local models: ‹what you need›
- Model Management
Use Ollama to pull GGUF quantized models: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/ollama/ollama
Call the API
Auth None needed
Its page: github.com/ollama/ollama
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- None
- Skills
- 3
Skills
Local Model Serving
Serve 100+ open-source LLMs locally with one command; auto-downloads models on first request.
OpenAI-Compatible API
Call local models via the same endpoints as OpenAI — drop-in replacement for any OpenAI SDK integration.
Model Management
Pull, list, copy, delete, and inspect GGUF quantized models from the Ollama model registry.