Parameters
2.2B
Weights (est.)
≈ 4.4 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Qwen2-VL-2B-mlx --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Qwen/Qwen2-VL-2B (finetune)
- Vendor
- Qwen
- Task
- Vision + text
- Quantisation
- Not stated
- Licence
- apache-2.0
- Downloads
- 76 in the last 30 days · 413 all time · 3 likes
- Published
- 2026-09-20 · updated 2026-09-21 (1mo ago)
- Languages
- en
- Tags
- qwen2_vl, multimodal
Other MLX builds of Qwen/Qwen2-VL-2B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen2-VL-2B-mlx (this one) | — | ≈ 4.4 GB | 8 GB+ | 76 |
| UGround-V1-2B | — | ≈ 4.4 GB | 8 GB+ | 32 |