Run frontier AI locally.
Splits one model across several of your devices, behind OpenAI, Claude and Ollama compatible APIs.
- Linguagem
- Python
- Licença
- Apache-2.0
- Estrelas
- 48k
- Última release
- v1.0.71
- Último push
- 2026-10-06
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
| Ferramenta | Substituição | Estrelas | Licença | Termos | Auto-hospedado | Linguagem | Última release | Último push |
|---|---|---|---|---|---|---|---|---|
| exo | Parcial | 48k | Apache-2.0 | Código aberto | Sim | Python | v1.0.71 | 2026-10-06 |
| llamafile | Parcial | 26k | Other | Código aberto | Sim | C++ | 0.10.6 | 2026-10-06 |
| MLC LLM | Parcial | 23k | Apache-2.0 | Código aberto | Sim | Python | v0.20.0 | 2026-10-04 |
3 alternativas
Run frontier AI locally.
Splits one model across several of your devices, behind OpenAI, Claude and Ollama compatible APIs.
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.