Docs
Browse documentation

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 3.14 on macOS, Linux, and Windows. The package is Apache-2.0 licensed and installs the fermion command. On Linux the CPU speech engine needs glibc 2.28 or newer (Ubuntu 18.10 or newer, Debian 10+, RHEL 8+). Phonon-1 needs about 7 GB of free RAM.

shell
pip install --no-deps torch --index-url https://download.pytorch.org/whl/cpu
pip install fermion-research

Install and chat

shell
pip install fermion-research
fermion chat neutrino-8b

The first command installs the package. The second downloads Neutrino-8B when needed, verifies it, selects the best available backend, and opens the interactive prompt.

  • /exit leaves the chat.
  • /reset clears the conversation history.
  • Name the model in every command, as in fermion chat neutrino-8b.

Generate one response

shell
fermion generate neutrino-8b "Explain why the sky is blue." --max-new 64

generate 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 info

fermion info checks the container structure, expected length, and SHA-256. It exits with status 1 if the container is truncated or altered.

What happens on first run

  1. 1

    Fetch metadata

    Configuration, tokenizer files, the model manifest, license, and the runner for the current platform arrive first.
  2. 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. 3

    Verify

    The expanded container is checked against the released SHA-256 before it is loaded.
  4. 4

    Select a backend

    The CLI reports whether it selected the optimized native path or the PyTorch reference path.

Speech

shell
fermion transcribe phonon-2 meeting.wav
fermion listen phonon-2

The same package runs Phonon-2, an open speech recognition model for English and the default for every speech command. transcribe prints the transcript of an audio file to standard output. listen transcribes the microphone live and prints the full transcript when you stop with Ctrl-C. Phonon-2 downloads on first use in 164 MB and runs on Apple silicon through MLX and on the CPU of a Mac, Linux, or Windows machine.

Transcribe and dictate covers both commands, the audio API, and the model options.