---
title: fishaudio/drama-3
url: https://recentmodel.com/models/fishaudio/drama-3/
status: main board
published: 2026-10-01T04:34:57Z
updated: 2026-10-01T04:34:57Z
source: https://huggingface.co/fishaudio/drama-3
---

# fishaudio/drama-3

Fish Audio Drama 3 is Fish Audio's new-generation text-to-speech model, built for multi-character scenes and long-form content. Mixture-of-experts, 36B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: fish-audio-research-license.


- **Org:** fishaudio
- **Released:** 2026-10-01
- **Status:** main board
- **License:** fish-audio-research-license (restricted)
- **Parameters:** 35.9B total, 3.0B active
- **Architecture:** MoE · 256 experts, 8/token · FishOmniModel
- **Context:** 262,144 tokens
- **Task:** text-to-speech · audio
- **Signal:** 1005 HF likes · 21375 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~25.5 GB: 32GB GPU (5090), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~40.2 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~73.3 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/fishaudio/drama-3)
- [quant: fishaudio/drama-3-int4](https://huggingface.co/fishaudio/drama-3-int4)
- [MLX: mlx-community/fish-audio-drama-3-3bit](https://huggingface.co/mlx-community/fish-audio-drama-3-3bit)
- [MLX: mlx-community/fish-audio-drama-3-4bit](https://huggingface.co/mlx-community/fish-audio-drama-3-4bit)
- [MLX: mlx-community/fish-audio-drama-3-8bit](https://huggingface.co/mlx-community/fish-audio-drama-3-8bit)