MLX Community · First MLX build 2 Nov 2026
HeartMuLa-oss-3B
MLX
Audio apache-2.0 New
A 3.9B parameter text to audio model, with 2 MLX builds, from 8-bit to bf16.
- Parameters
- 3.9B From Hugging Face
- Quantisation
- bf16 HeartMuLa-oss-3B-bf16
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.9 GB Weights, estimated
- Downloads
- 124 This build, last 30 days
- Task
- Text to audio Audio
- MLX builds
- 2 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/HeartMuLa-oss-3B-bf16MLX builds
2 on mlx-community| HeartMuLa-oss-3B-8bit | 8-bit | 4.9 GB | 8 GB | 107 |
|---|---|---|---|---|
| HeartMuLa-oss-3B-bf16 | bf16 | 7.9 GB | 11 GB | 124 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.