MLX Community · First MLX build 8 Mar 2024
whisper-small.en
MLX
A model, with 5 MLX builds, from 4-bit to fp32.
- Parameters
- — Not published
- Quantisation
- Unstated whisper-small.en-mlx
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 16K This build, last 30 days
- Task
- —
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/whisper-small.en-mlxMLX builds
5 on mlx-community| whisper-small.en-mlx | Unstated | — | — | 16K |
|---|---|---|---|---|
| whisper-small.en-mlx-q4 | 4-bit | — | — | 313 |
| whisper-small.en-mlx-4bit | 4-bit | — | — | 183 |
| whisper-small.en-mlx-8bit | 8-bit | — | — | 92 |
| whisper-small.en-mlx-fp32 | fp32 | — | — | 42 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.