4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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/bu-30b-a3b-preview-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- browser-use/bu-30b-a3b-preview (quantized)
- Vendor
- browser-use
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 44 in the last 30 days · 646 all time · 4 likes
- Published
- 2025-12-17 · updated 2025-12-17 (10mo ago)
- Languages
- en
- Tags
- qwen3_vl_moe, browser_use
Other MLX builds of browser-use/bu-30b-a3b-preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| bu-30b-a3b-preview-4bit (this one) | 4-bit | — | — | 44 |
| bu-30b-a3b-preview-8bit | 8-bit | — | — | 24 |