# Moonshine Tiny Benchmark Scores & Performance

> Moonshine Tiny has Fermion speech evaluation results. Voice evidence is display-only and does not produce a text-model score.

Canonical page: https://benchlm.ai/models/moonshine-tiny

Last updated: September 30, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Useful Sensors |
| Source Type | Open Weight |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [Useful Sensors model documentation](https://huggingface.co/UsefulSensors/moonshine-tiny) |
| Overall Score | Not scored (voice evidence only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Moonshine Tiny
- Variant: base
- Benchmarks covered: 0 of 486
- Coverage note: Speech and voice results appear below; no weighted text-model benchmark rows are stored.

## Speech and voice evidence

[Phonon-2 launch evaluation](/voice-benchmarks/phonon-2-launch-evaluation)

Fermion ran Phonon-2, Phonon-1, and Parakeet Redux with the Open ASR Leaderboard code on full test sets. The other accuracy rows are leaderboard figures quoted by Fermion, without independent re-verification here. Some model cards report different runs; those values are not mixed into this comparison. Voxtral's download size is an estimate at 16 bits. Throughput includes log-mel processing and excludes model load; batch-128 GPU results are separate from single-stream results. The Mac runtime comparison uses 20 dictations totaling 797 seconds at each runtime's defaults. Download size does not measure runtime memory. These results do not enter text-model or voice-agent rankings.

| Metric | Result |
| --- | --- |
| M5 MacBook Air throughput | 26.7x realtime |
| Accuracy in this comparison | Not measured |

Fermion runtime comparison retrieved September 30, 2026; 20 dictations, 797 seconds of speech, one stream at a time, model load excluded.

- [Evaluation source](https://www.fermionresearch.com/research/phonon-2/)

Open English speech recognition weights under MIT. Useful Sensors documents 27 million parameters and an October 2024 release. Fermion reports speed on its M5 MacBook Air dictation test, without an accuracy row for this model.