Run frontier AI locally.
Splits one model across several of your devices, behind OpenAI, Claude and Ollama compatible APIs.
- Sprache
- Python
- Lizenz
- Apache-2.0
- Sterne
- 48k
- Neuestes Release
- v1.0.71
- Letzter Push
- 2026-10-06
Alternativen zu
Ollama
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Im Vergleich
| Tool | Ersatzgrad | Sterne | Lizenz | Bedingungen | Selbst hostbar | Sprache | Neuestes Release | Letzter Push |
|---|---|---|---|---|---|---|---|---|
| exo | Teilweise | 48k | Apache-2.0 | Open Source | Ja | Python | v1.0.71 | 2026-10-06 |
| llamafile | Teilweise | 26k | Other | Open Source | Ja | C++ | 0.10.6 | 2026-10-06 |
| MLC LLM | Teilweise | 23k | Apache-2.0 | Open Source | Ja | Python | v0.20.0 | 2026-10-04 |
Alle Alternativen
3 Alternativen
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.
- Sprache
- Python
- Lizenz
- Apache-2.0
- Sterne
- 23k
- Neuestes Release
- v0.20.0
- Letzter Push
- 2026-10-04
Direkt verglichen
Über Ollama
- Sprache
- Go
- Lizenz
- MIT
- Sterne
- 182k
- Letzter Push
- 2026-10-06