Downloads · 30 days
135
7% of all-time downloads
Qwen3-VL-Embedding-2B-mlx-4bit
arthurcollet/Qwen3-VL-Embedding-2B-mlx-4bit
Qwen3-VL-Embedding-2B-mlx-4bit is a feature extraction model from arthurcollet. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
This model was converted to MLX format from Qwen/Qwen3-VL-Embedding-2B using mlx-vlm version 0.3.11. Refer to the original model card for more details on the model.
All-time downloads
2K
Public
Parameters
2.1B
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.8 GB · 99%
Parameter types
How the weights are stored.
U321.7B · 81%
Base models
Model card
From the Hugging Face model README
arthurcollet/Qwen3-VL-Embedding-2B-mlx-4bit
This model was converted to MLX format from Qwen/Qwen3-VL-Embedding-2B using mlx-vlm version 0.3.11.
Refer to the original model card for more details on the model.
Use with mlx
pip install -U mlx-vlm
python -m mlx_vlm.generate --model arthurcollet/Qwen3-VL-Embedding-2B-mlx-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
- Task
- Feature Extraction
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jan 13, 2026
- Updated
- Feb 9, 2026