# Phonon-2 brings on-device ASR to Apple Silicon

> A low-bit quantized, Parakeet-based speech recognizer built to run locally on Mac hardware.

Published by The Open Weights on Sep 28, 2026. Canonical: https://theopenweights.com/news/phonon-2-prj5

## Key facts

- Company: FermionResearch
- Model: Phonon-2
- Version: 2
- Category: Speech → Text
- Modalities: Speech → Text
- License: Other (Open weights, commercial use allowed)
- Parameters: 600M
- Architecture: parakeet_tdt_five_value
- Languages: English
- Significance: minor
- Published: 2026-09-28
- Last verified: 2026-10-07
- Hugging Face: https://huggingface.co/FermionResearch/Phonon-2
- Canonical URL: https://theopenweights.com/news/phonon-2-prj5

FermionResearch has published [Phonon-2](https://huggingface.co/FermionResearch/Phonon-2), a compact automatic speech recognition model designed to run locally on Apple Silicon. The model is built on NVIDIA's Parakeet ASR architecture and shipped in a low-bit quantized form, with roughly 600 million parameters and a focus on English transcription.

The pitch here is practical rather than flashy: instead of streaming audio to a cloud endpoint, Phonon-2 aims to do the work on the device itself. For developers building Mac-native apps — note-takers, captioning tools, voice interfaces — that means lower latency, no per-request API cost, and audio that never leaves the machine.

## Why it matters

Parakeet has earned a reputation as one of the stronger open ASR families, but running it well on consumer hardware has usually meant trimming it down. Phonon-2's low-bit quantization is the lever that makes a sub-gigabyte footprint feasible on Apple's unified-memory chips.

- Architecture derived from NVIDIA's Parakeet ASR line
- About 0.6B parameters, quantized to low precision
- English-only, optimized for on-device Apple Silicon inference

The release is distributed under a non-standard license, so teams planning commercial use should read the terms on the [model card](https://huggingface.co/FermionResearch/Phonon-2) before shipping. For anyone who wants fast, private transcription without a server bill, it's a notable addition to the on-device toolkit.

## Get the model

- [Hugging Face](https://huggingface.co/FermionResearch/Phonon-2)

## Sources

- [FermionResearch/Phonon-2](https://huggingface.co/FermionResearch/Phonon-2) — Hugging Face, Sep 28, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Phonon-2 brings on-device ASR to Apple Silicon", The Open Weights, Sep 28, 2026, https://theopenweights.com/news/phonon-2-prj5