Parameters
8.3B
Weights (est.)
≈ 16.6 GB
Mac memory (est.)
24 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/numind-NuExtract-2.0-8B-MLX --image photo.jpg --prompt "Describe this image"
Details
- Base model
- numind/NuExtract-2.0-8B (finetune)
- Vendor
- numind
- Task
- Vision + text
- Quantisation
- Not stated
- Licence
- mit
- Downloads
- 38 in the last 30 days · 248 all time · 0 likes
- Published
- 2026-04-14 · updated 2026-04-14 (7mo ago)
- Languages
- en
- Tags
- qwen2_5_vl, mlx-vlm, multimodal, document-understanding, unquantized