ShowUI-2B-bf16-4bit
mlx-community/ShowUI-2B-bf16-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
2.2B
Weights (est.)
≈ 2.2 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.
Details
- Base model
- Qwen/Qwen2-VL-2B-Instruct (finetune)
- Vendor
- Qwen
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 54 in the last 30 days · 337 all time · 0 likes
- Published
- 2025-02-26 · updated 2025-02-26 (1y ago)
- Tags
- qwen2_vl, GUI agents, vision-language-action model, computer use
Other MLX builds of Qwen/Qwen2-VL-2B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ShowUI-2B-bf16-4bit (this one) | 4-bit | ≈ 2.2 GB | 8 GB+ | 54 |
| ShowUI-2B-bf16-6bit | 6-bit | ≈ 2.6 GB | 8 GB+ | 30 |
| ShowUI-2B-bf16-8bit | 8-bit | ≈ 3.0 GB | 8 GB+ | 55 |
| ShowUI-2B-bf16 | bf16 | ≈ 4.4 GB | 8 GB+ | 32 |