bf16 Open on Hugging Face
Parameters
4.5B
Weights (est.)
≈ 9.1 GB
Mac memory (est.)
16 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/NuExtract3-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- numind/NuExtract3 (finetune)
- Vendor
- numind
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- —
- Downloads
- 61 in the last 30 days · 446 all time · 0 likes
- Published
- 2026-05-20 · updated 2026-05-20 (5mo ago)
- Tags
- qwen3_5, mlx-vlm, bfloat16, nuextract