MLX Community · First MLX build 30 May 2026
belle-distil-whisper-large-v2-zh
MLX
Audio apache-2.0
A 754M parameter speech recognition model, with 2 MLX builds, from 8-bit to fp16.
- Parameters
- 754M From Hugging Face
- Quantisation
- 8-bit belle-distil-whisper-large-v2-zh-8bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 807 MB Weights, estimated
- Downloads
- 11 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/belle-distil-whisper-large-v2-zh-8bitMLX builds
2 on mlx-community| belle-distil-whisper-large-v2-zh-8bit | 8-bit | 807 MB | 3 GB | 11 |
|---|---|---|---|---|
| belle-distil-whisper-large-v2-zh-fp16 | fp16 | 1.5 GB | 4 GB | 11 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.