MLX Community · First MLX build 24 Mar 2025
Qwen2.5-VL-32B-Instruct
MLX
TextVision apache-2.0
A vision and text model, with 4 MLX builds, from 4-bit to 6-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit Qwen2.5-VL-32B-Instruct-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 830 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 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 · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Qwen2.5-VL-32B-Instruct-4bit --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| Qwen2.5-VL-32B-Instruct-4bit | 4-bit | — | — | 830 |
|---|---|---|---|---|
| Qwen2.5-VL-32B-Instruct-bf16 | bf16 | — | — | 207 |
| Qwen2.5-VL-32B-Instruct-8bit | 8-bit | — | — | 145 |
| Qwen2.5-VL-32B-Instruct-6bit | 6-bit | — | — | 112 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.