m-a-p · First MLX build 28 Oct 2026
YuE2-3B
MLX
Audio cc-by-nc-4.0
A 3.6B parameter text to audio model from m-a-p, with one MLX build at bf16.
- Parameters
- 3.6B From Hugging Face
- Quantisation
- bf16 YuE2-3B-bf16
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.3 GB Weights, estimated
- Downloads
- 101 This build, last 30 days
- Task
- Text to audio Audio
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 11 GB at bf16
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/YuE2-3B-bf16MLX builds
1 on mlx-community| YuE2-3B-bf16 | bf16 | 7.3 GB | 11 GB | 101 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.