bf16 Open on Hugging Face
Parameters
2.4B
Weights (est.)
≈ 4.9 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/ShowUI-2B-bf16-v2 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- showlab/ShowUI-2B (finetune)
- Vendor
- showlab
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- mit
- Downloads
- 23 in the last 30 days · 135 all time · 0 likes
- Published
- 2026-03-20 · updated 2026-03-20 (7mo ago)
- Languages
- en
- Tags
- qwen2_vl, mlx-vlm, apple-silicon, vision-language-model, showui, gui-agents, vision-language-action, computer-use, grounding, bf16
Other MLX builds of showlab/ShowUI-2B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ShowUI-2B-6bit-v2 | 6-bit | ≈ 2.8 GB | 8 GB+ | 37 |
| ShowUI-2B-bf16-v2 (this one) | bf16 | ≈ 4.9 GB | 8 GB+ | 23 |