MLX Community · First MLX build 10 Dec 2025
VoxCPM1.5
MLX
Audio apache-2.0
A 888M parameter text to speech model, with 6 MLX builds, from 4-bit to fp16.
- Parameters
- 888M From Hugging Face
- Quantisation
- 4-bit VoxCPM1.5-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 623 MB Weights, estimated
- Downloads
- 112 This build, last 30 days
- Task
- Text to speech Audio
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 4-bit
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/VoxCPM1.5-4bitMLX builds
6 on mlx-community| VoxCPM1.5-4bit | 4-bit | 623 MB | 3 GB | 112 |
|---|---|---|---|---|
| VoxCPM1.5-5bit | 5-bit | 723 MB | 3 GB | 20 |
| VoxCPM1.5-6bit | 6-bit | 824 MB | 3 GB | 17 |
| VoxCPM1.5-8bit | 8-bit | 1.0 GB | 4 GB | 66 |
| VoxCPM1.5 | Unstated | 1.9 GB | 5 GB | 89 |
| VoxCPM1.5-fp16 | fp16 | 1.9 GB | 5 GB | 29 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.