MLX Community · First MLX build 19 Dec 2025
GLM-ASR-Nano-2512
MLX
Audio mit
A 2.3B parameter speech recognition model, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 2.3B From Hugging Face
- Quantisation
- 8-bit GLM-ASR-Nano-2512-8bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.4 GB Weights, estimated
- Downloads
- 113 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 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/GLM-ASR-Nano-2512-8bitMLX builds
4 on mlx-community| GLM-ASR-Nano-2512-4bit | 4-bit | 1.3 GB | 4 GB | 112 |
|---|---|---|---|---|
| GLM-ASR-Nano-2512-5bit | 5-bit | 1.6 GB | 4 GB | 20 |
| GLM-ASR-Nano-2512-6bit | 6-bit | 1.8 GB | 5 GB | 13 |
| GLM-ASR-Nano-2512-8bit | 8-bit | 2.4 GB | 5 GB | 113 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.