inclusionAI · First MLX build 19 Oct 2026
Ming-3.0-asr-tiny
MLX
Audio mit
A 8.5B parameter speech recognition model from inclusionAI, with one MLX build at bf16.
- Parameters
- 8.5B From Hugging Face
- Quantisation
- bf16 Ming-3.0-asr-tiny-bf16
- Memory needed
- 22 GB Estimate, unified memory
- Download
- 17.1 GB Weights, estimated
- Downloads
- 148 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 22 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/Ming-3.0-asr-tiny-bf16MLX builds
1 on mlx-community| Ming-3.0-asr-tiny-bf16 | bf16 | 17.1 GB | 22 GB | 148 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.