MLX Community · First MLX build 14 Jan 2026
whisper-large-asr
MLX
Audio apache-2.0
A 1.5B parameter speech recognition model, with 5 MLX builds, from 4-bit to fp16.
- Parameters
- 1.5B From Hugging Face
- Quantisation
- fp16 whisper-large-asr-fp16
- Memory needed
- 6 GB Estimate, unified memory
- Download
- 3.1 GB Weights, estimated
- Downloads
- 16 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 6 GB at fp16
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/whisper-large-asr-fp16MLX builds
5 on mlx-community| whisper-large-asr-4bit | 4-bit | 877 MB | 3 GB | 15 |
|---|---|---|---|---|
| whisper-large-asr-5bit | 5-bit | 1.1 GB | 4 GB | 7 |
| whisper-large-asr-6bit | 6-bit | 1.3 GB | 4 GB | 7 |
| whisper-large-asr-8bit | 8-bit | 1.6 GB | 4 GB | 13 |
| whisper-large-asr-fp16 | fp16 | 3.1 GB | 6 GB | 16 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.