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
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Côte à côte
| Outil | Remplacement | Étoiles | Licence | Conditions | Auto-hébergeable | Langage | Dernière release | Dernier push |
|---|---|---|---|---|---|---|---|---|
| exo | Partiel | 48k | Apache-2.0 | Open source | Oui | Python | v1.0.71 | 2026-10-06 |
| llamafile | Partiel | 26k | Other | Open source | Oui | C++ | 0.10.6 | 2026-10-06 |
| MLC LLM | Partiel | 23k | Apache-2.0 | Open source | Oui | Python | v0.20.0 | 2026-10-04 |
Toutes les alternatives
3 alternatives
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
Face à face
À propos de Ollama
- Langage
- Go
- Licence
- MIT
- Étoiles
- 182k
- Dernier push
- 2026-10-06