MLX Community · First MLX build 23 Jan 2026
VibeVoice-ASR
MLX
Audio mit
A 8.3B parameter speech recognition model, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 8.3B From Hugging Face
- Quantisation
- 4-bit VibeVoice-ASR-4bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.7 GB Weights, estimated
- Downloads
- 866 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 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/VibeVoice-ASR-4bitMLX builds
5 on mlx-community| VibeVoice-ASR-4bit | 4-bit | 5.7 GB | 9 GB | 866 |
|---|---|---|---|---|
| VibeVoice-ASR-5bit | 5-bit | 6.7 GB | 10 GB | 12 |
| VibeVoice-ASR-6bit | 6-bit | 7.6 GB | 11 GB | 23 |
| VibeVoice-ASR-8bit | 8-bit | 9.5 GB | 13 GB | 322 |
| VibeVoice-ASR-bf16 | bf16 | 16.7 GB | 21 GB | 217 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.