bf16 Open on Hugging Face
Parameters
8.8B
Weights (est.)
≈ 17.5 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/MAI-UI-8B-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Tongyi-MAI/MAI-UI-8B (finetune)
- Vendor
- Tongyi-MAI
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- apache-2.0
- Downloads
- 27 in the last 30 days · 299 all time · 0 likes
- Published
- 2026-03-20 · updated 2026-03-20 (7mo ago)
- Languages
- en
- Tags
- qwen3_vl, mlx-vlm, apple-silicon, vision-language-model, mai-ui, grounding, mobile-navigation, computer-use, agent, bf16
Other MLX builds of Tongyi-MAI/MAI-UI-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MAI-UI-8B-4bit | 4-bit | ≈ 6.9 GB | 16 GB+ | 35 |
| MAI-UI-8B-6bit | 6-bit | ≈ 9.0 GB | 16 GB+ | 32 |
| MAI-UI-8B-bf16 (this one) | bf16 | ≈ 17.5 GB | 24 GB+ | 27 |