Docs / Getting started
Install and run Neutrino
Install fermion, open a local chat, and verify the downloaded model in about a minute.
Requirements
Fermion supports Python 3.10 through 3.13 on macOS and Linux. The package is Apache-2.0 licensed and installs the fermion command.
shell
pip install torch --index-url https://download.pytorch.org/whl/cpu
pip install fermion-researchInstall and chat
shell
pip install fermion-research
fermion chatThe first command installs the package. The second downloads Neutrino-8B when needed, verifies it, selects the best available backend, and opens the interactive prompt.
/exitleaves the chat./resetclears the conversation history.- The default model is
FermionResearch/Neutrino-8B.
Generate one response
shell
fermion generate "Explain why the sky is blue." --max-new 64generate is deterministic by default and prints the completion to standard output. Runtime and throughput statistics go to standard error, which keeps scripts clean.
Verify the installation
shell
fermion --version
fermion infofermion info checks the container structure, expected length, and SHA-256. It exits with status 1 if the artifact is truncated or altered.
What happens on first run
- 1
Fetch metadata
Configuration, tokenizer files, the model manifest, license, and the runner for the current platform arrive first. - 2
Download weights
Apple Silicon downloads a 2.56 GB coded transport and expands it locally. Other platforms download the 3.88 GB container. - 3
Verify
The expanded artifact is checked against the released SHA-256 before it is loaded. - 4
Select a backend
The CLI reports whether it selected the optimized native path or the PyTorch reference path.