FunAudioLLM · First MLX build 16 Dec 2025
Fun-CosyVoice3-0.5B-2512
MLX
Audio
A 866M parameter text to speech model from FunAudioLLM, with 3 MLX builds, from 4-bit to fp16.
- Parameters
- 866M From Hugging Face
- Quantisation
- fp16 Fun-CosyVoice3-0.5B-2512-fp16
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.7 GB Weights, estimated
- Downloads
- 701 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at fp16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Fun-CosyVoice3-0.5B-2512-fp16MLX builds
3 on mlx-community| Fun-CosyVoice3-0.5B-2512-4bit | 4-bit | 1.2 GB | 4 GB | 554 |
|---|---|---|---|---|
| Fun-CosyVoice3-0.5B-2512-8bit | 8-bit | 1.4 GB | 4 GB | 465 |
| Fun-CosyVoice3-0.5B-2512-fp16 | fp16 | 1.7 GB | 4 GB | 701 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.