---
library_name: mlx-audio
tags:
- mlx
- mlx-audio
- text-to-speech
- speech
- speech-generation
- voice-cloning
- tts
- fish-audio
- s2-pro
- quantized
- 4bit
- fish_qwen3_omni
base_model: fishaudio/s2-pro
license: other
license_name: fish-audio-research
license_link: https://huggingface.co/fishaudio/s2-pro/blob/main/LICENSE
pipeline_tag: text-to-speech
language:
- en
- zh
- ja
- ko
- es
- pt
- ar
- ru
- fr
- de
---

# Fish Audio S2 Pro MLX 4-bit

MLX 4-bit quantization of [fishaudio/s2-pro](https://huggingface.co/fishaudio/s2-pro), produced with [mlx-audio](https://github.com/Blaizzy/mlx-audio) on Apple Silicon.

**Built with Fish Audio.**

## Provenance

Converted directly from `fishaudio/s2-pro` bf16 safetensors via `python -m mlx_audio.convert ... -q --q-bits 4 --q-group-size 64`. The `codec.pth` audio decoder, tokenizer, and chat template are preserved alongside the quantized LLM weights.

## Quantization

- Method: MLX affine quantization, group_size=64, 4-bit
- Actual bits per weight after conversion: **~5.0** (some small projections are skipped and remain bf16 — this is expected behavior for mlx.nn.quantize on multimodal models)
- Size on disk: ~2.4 GB (vs ~8 GB for bf16)
- Target: Apple Silicon with ≥ 16 GB unified memory (comfortable on M-series with 24 GB+)

## Architecture

`fish_qwen3_omni` — a Qwen3-based decoder-only LLM that emits audio tokens consumed by the `codec.pth` DualAR codec. The text side is quantized; the codec is kept as-is.

## Quickstart

```python
from mlx_audio.tts import load

model = load("majentik/fishaudio-s2-pro-MLX-4bit")
audio = model.generate(
    text="Hello, this is a test of Fish S2 Pro at 4-bit MLX.",
    voice="en_default",
)
```

Fish S2 Pro supports zero-shot voice cloning from a reference audio sample; see the base model card for the reference-conditioning API.

## License & Use Restrictions

This model is a derivative work of **Fish Audio S2 Pro**, licensed under the **Fish Audio Research License**.

- **Research + Non-Commercial use:** free, subject to the license.
- **Commercial use:** requires a separate written agreement with Fish Audio — see https://fish.audio or email `business@fish.audio`.
- **Use restriction:** outputs must not be used to create or improve any foundational generative AI model (excluding the Model itself or derivatives of it).
- **Attribution:** downstream use must include this NOTICE and display "Built with Fish Audio" in any product/service/interface that surfaces model outputs.

See `LICENSE.md` and `NOTICE` files bundled with this repository.

## Languages

English, Chinese, Japanese, Korean, Spanish, Portuguese, Arabic, Russian, French, German (per base model card).

## See also

- Base: [fishaudio/s2-pro](https://huggingface.co/fishaudio/s2-pro)
- bf16 MLX: [mlx-community/fish-audio-s2-pro-bf16](https://huggingface.co/mlx-community/fish-audio-s2-pro-bf16)
- 8-bit MLX: [mlx-community/fishaudio-s2-pro-8bit-mlx](https://huggingface.co/mlx-community/fishaudio-s2-pro-8bit-mlx)
- mlx-audio: https://github.com/Blaizzy/mlx-audio
- Garden hub: [majentik/garden](https://huggingface.co/majentik/garden)