openbmb · First MLX build 8 Apr 2026
VoxCPM2
MLX
Audio apache-2.0 Trending
A 2.4B parameter text to speech model from openbmb, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 2.4B From Hugging Face
- Quantisation
- 8-bit VoxCPM2-8bit
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 3.2 GB Weights, estimated
- Downloads
- 9.8K 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 6 GB at 8-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/VoxCPM2-8bitMLX builds
3 on mlx-community| VoxCPM2-4bit | 4-bit | 2.3 GB | 5 GB | 1.8K |
|---|---|---|---|---|
| VoxCPM2-8bit | 8-bit | 3.2 GB | 6 GB | 9.8K |
| VoxCPM2-bf16 | bf16 | 5.0 GB | 8 GB | 3.5K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.