Docs / Reference
Model reference
The three Neutrino repositories, their runnable artifacts, and the integration each file is intended for.
Neutrino-1 8B
The default general model and the only Neutrino-1 model that reliably emits tool calls. The trained context window is 40,960 positions.
| Artifact | Size | Used by |
|---|---|---|
| neutrino-8b_v4.bin | 3.88 GB | fermion native and PyTorch paths, plus MLX |
| neutrino-8b_v4.tv4z | 2.56 GB | Apple Silicon download transport |
| neutrino-8b-fv5.gguf | 4.09 GB | Fermion llama.cpp fork |
| bin/fermion-run-* | about 2 MB each | Optimized native runtime |
| MANIFEST.json and SHA sidecars | small | Integrity checks |
Neutrino-1 0.6B
A 328 MB small model and the canonical --draft auto target. It can also run independently through chat, generate, serve, the native runners, or the model repository’s MLX pack.
- Runnable container: 328 MB
- Coded transport: 238 MB
- GGUF: 343 MB
Neutrino-1 0.6B-Chat
A 328 MB conversational small model. It ships native runners and MLX code. It does not currently ship GGUF weights and should not be selected for reliable tool calling.
Open Neutrino-0.6B-Chat on Hugging FaceLicense and base model
The package and model releases use Apache-2.0. Neutrino-1 8B is derived from Qwen3-8B, which uses the same license.