FunAudioLLM · First MLX build 16 Dec 2025
Fun-ASR-MLT-Nano-2512
MLX
Audio
A 985M parameter speech recognition model from FunAudioLLM, with 3 MLX builds, from 4-bit to fp16.
- Parameters
- 985M From Hugging Face
- Quantisation
- 8-bit Fun-ASR-MLT-Nano-2512-8bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.5 GB Weights, estimated
- Downloads
- 73 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 4 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/Fun-ASR-MLT-Nano-2512-8bitMLX builds
3 on mlx-community| Fun-ASR-MLT-Nano-2512-4bit | 4-bit | 1.3 GB | 4 GB | 30 |
|---|---|---|---|---|
| Fun-ASR-MLT-Nano-2512-8bit | 8-bit | 1.5 GB | 4 GB | 73 |
| Fun-ASR-MLT-Nano-2512-fp16 | fp16 | 2.0 GB | 5 GB | 47 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.