Alibaba Qwen · First MLX build 28 Mar 2026
Qwen2-Audio-7B-Instruct
MLX
TextAudio apache-2.0
A audio and text model from Alibaba Qwen, with one MLX build at 4-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit Qwen2-Audio-7B-Instruct-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 4.6K This build, last 30 days
- Task
- Audio and text Text, Audio
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/Qwen2-Audio-7B-Instruct-4bitMLX builds
1 on mlx-community| Qwen2-Audio-7B-Instruct-4bit | 4-bit | — | — | 4.6K |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.