Run frontier AI locally.
Splits one model across several of your devices, behind OpenAI, Claude and Ollama compatible APIs.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 48k
- Dernière release
- v1.0.71
- Dernier push
- 2026-10-06
Ollama
Distribute and run LLMs with a single file.
Packs llama.cpp and a model into one executable that runs on most systems, with a local API and web chat.
Universal LLM Deployment Engine with ML Compilation
Compiles models for GPUs, phones and browsers, and serves them behind an OpenAI-compatible API.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 23k
- Dernière release
- v0.20.0
- Dernier push
- 2026-10-04
Chargement du README
- v0.40.0-rc62026-09-25v0.40.0pré-release
- v0.35.12026-09-29Ollama now supports Clef and Clef Flash, Cloudflare's new open-source decision models, through /v1/systemone.
- v0.35.02026-09-28Ollama now supports decision models through /v1/systemone, based on TypeSafe’s Jev API.
- v0.34.42026-09-23Structured outputs on thinking models now apply in a single pass, making them faster and more reliable.
- v0.34.32026-09-19GET /api/show now advertises each model's thinking controls and default:
✓ signée La dernière release, v0.35.1, porte une signature vérifiée par GitHub.
Chargement du rapport de sécurité