MLX Community · First MLX build 29 Jan 2026
Qwen3-ASR-1.7B
MLX
apache-2.0 Trending
A 2B parameter model, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 2B From Hugging Face
- Quantisation
- 8-bit Qwen3-ASR-1.7B-8bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.5 GB Weights, estimated
- Downloads
- 13K This build, last 30 days
- Task
- —
- MLX builds
- 5 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/Qwen3-ASR-1.7B-8bitMLX builds
5 on mlx-community| Qwen3-ASR-1.7B-4bit | 4-bit | 1.6 GB | 4 GB | 3.2K |
|---|---|---|---|---|
| Qwen3-ASR-1.7B-5bit | 5-bit | 1.8 GB | 5 GB | 241 |
| Qwen3-ASR-1.7B-6bit | 6-bit | 2.0 GB | 5 GB | 697 |
| Qwen3-ASR-1.7B-8bit | 8-bit | 2.5 GB | 5 GB | 13K |
| Qwen3-ASR-1.7B-bf16 | bf16 | 4.1 GB | 7 GB | 3.7K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.