Docs / Getting started
Models, downloads, and storage
Know what the CLI downloads, where it stores the files, and how much free space the first run needs.
Released models
| Model | Runnable container | Coded transport | Primary use |
|---|---|---|---|
| Neutrino-1 8B | 3.88 GB | 2.56 GB | Default general model and tool caller |
| Neutrino-1 0.6B | 328 MB | 238 MB | Small model and canonical speculative draft |
| Neutrino-1 0.6B-Chat | 328 MB | 238 MB | Small conversational model |
Speech models
Every speech command names its model first, as in fermion transcribe phonon-2 meeting.wav, with a short alias, a repository id, or a local model directory, and fermion models lists every published model and marks the ones already on the machine.
| Model | Download | On disk | Aliases |
|---|---|---|---|
| Phonon-2 | 164 MB | 178 MB | phonon-2, phonon2, phonon, speech, stt, asr |
| Phonon-1 | 415 MB | 455 MB | phonon-1 |
| Phonon-1-Big | 581 MB | 822 MB | phonon-1-big, phonon-big, big |
| Phonon-1-Micro | 285 MB | 331 MB | phonon-1-micro, phonon-micro, micro |
fermion models
fermion transcribe phonon-2 meeting.wav
fermion transcribe FermionResearch/Phonon-1-Big meeting.wavA speech model downloads as a single archive, checked against a SHA-256 pinned inside the package before it is unpacked, and every file is checked against the manifest before it is written; a failed checksum stops the install. The model unpacks under ~/.cache/fermion/speech; the archive itself sits in the Hugging Face hub cache. FERMION_CACHE_DIR and HF_HOME move both.
The first-run download plan
The CLI downloads only the files required to run the selected model. GGUF and MLX files are not fetched by default.
| Platform | Downloaded | Steady state | Peak free space |
|---|---|---|---|
| Apple Silicon | 2.56 GB transport | about 3.9 GB | about 6.5 GB |
| Other platforms | 3.88 GB container | about 3.9 GB | about 4 GB |
| 0.6B models | 238 MB transport or 328 MB container | 328 MB | under 600 MB |
On Apple Silicon, the verified transport is deleted after expansion. Set FERMION_KEEP_TRANSPORT=1 if you want to keep it. Set FERMION_DOWNLOAD_ALL=1 only when you intentionally want the whole repository.
Move the model cache
Models use the standard Hugging Face cache under ~/.cache/huggingface/hub. Move all Hugging Face data with HF_HOME, or move only Fermion model downloads with FERMION_CACHE_DIR.
export HF_HOME=/big/disk/hf
# or
export FERMION_CACHE_DIR=/big/disk/fermion
fermion chat neutrino-8bA small ~/.cache/fermion directory may also hold generated Transformers configuration directories.
Disk-space checks and interrupted downloads
Before downloading weights, fermion checks the real cache volume against the model manifest. If the volume is too small, it stops before the transfer and prints the cache path, required bytes, available bytes, and the two cache variables above.
If a download or local expansion is interrupted, run fermion info. The command detects incomplete structure and hash mismatches and exits non-zero for automation.