MLX Community · First MLX build 22 May 2026
Mega-ASR
MLX
Audio apache-2.0
A 2B parameter speech recognition model, with 3 MLX builds, from 6-bit to bf16.
- Parameters
- 2B From Hugging Face
- Quantisation
- bf16 Mega-ASR-bf16
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.1 GB Weights, estimated
- Downloads
- 85 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 GB at bf16
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/Mega-ASR-bf16MLX builds
3 on mlx-community| Mega-ASR-6bit | 6-bit | 2.0 GB | 5 GB | 27 |
|---|---|---|---|---|
| Mega-ASR-8bit | 8-bit | 2.5 GB | 5 GB | 50 |
| Mega-ASR-bf16 | bf16 | 4.1 GB | 7 GB | 85 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.