bf16 Open on Hugging Face
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/GUI-Owl-7B-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- mPLUG/GUI-Owl-7B (finetune)
- Vendor
- mPLUG
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- mit
- Downloads
- 29 in the last 30 days · 211 all time · 0 likes
- Published
- 2026-03-20 · updated 2026-03-20 (7mo ago)
- Languages
- en
- Tags
- qwen2_5_vl, mlx-vlm, apple-silicon, vision-language-model, gui-owl, mobile-agent-v3, computer-use, grounding, osworld, screenspot, bf16
Other MLX builds of mPLUG/GUI-Owl-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GUI-Owl-7B-6bit | 6-bit | ≈ 7.6 GB | 16 GB+ | 41 |
| GUI-Owl-7B-bf16 (this one) | bf16 | ≈ 16.6 GB | 24 GB+ | 29 |
| GUI-Owl-7B-4bit | 4-bit | — | — | 28 |