Downloads · 30 days
22
7% of all-time downloads
Qwen2.5-VL-3B-Instruct-mlx-4Bit
dicksonhk/Qwen2.5-VL-3B-Instruct-mlx-4Bit
Qwen2.5-VL-3B-Instruct-mlx-4Bit is a image-text-to-text model from dicksonhk. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.
The Model dicksonhk/Qwen2.5-VL-3B-Instruct-mlx-4Bit was converted to MLX format from Qwen/Qwen2.5-VL-3B-Instruct using mlx-vlm version 0.1.15.
All-time downloads
329
Public
Parameters
3.8B
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
Parameter types
How the weights are stored.
U323.6B · 96%
Try a prompt
Base models
Model card
From the Hugging Face model README
dicksonhk/Qwen2.5-VL-3B-Instruct-mlx-4Bit
The Model dicksonhk/Qwen2.5-VL-3B-Instruct-mlx-4Bit was converted to MLX format from Qwen/Qwen2.5-VL-3B-Instruct using mlx-vlm version 0.1.15.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model dicksonhk/Qwen2.5-VL-3B-Instruct-mlx-4Bit --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen2_5_vl
- Languages
- en
- Created
- Jun 19, 2025
- Updated
- Jun 19, 2025