Qwen-3-VL-Ricoh-8B-20260227-MLX-4bit
mlx-community/Qwen-3-VL-Ricoh-8B-20260227-MLX-4bit
Vision + text · mlx
4-bit Open on Hugging Face
Parameters
8.8B
Weights (est.)
≈ 5.8 GB
Mac memory (est.)
16 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/Qwen-3-VL-Ricoh-8B-20260227-MLX-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- ricoh-ai/Qwen-3-VL-Ricoh-8B-20260227 (quantized)
- Vendor
- ricoh-ai
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 51 in the last 30 days · 350 all time · 0 likes
- Published
- 2026-03-30 · updated 2026-03-30 (7mo ago)
- Languages
- ja
- Tags
- qwen3_vl
Other MLX builds of ricoh-ai/Qwen-3-VL-Ricoh-8B-20260227
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen-3-VL-Ricoh-8B-20260227-MLX-4bit (this one) | 4-bit | ≈ 5.8 GB | 16 GB+ | 51 |
| Qwen-3-VL-Ricoh-8B-20260227-MLX-8bit | 8-bit | ≈ 9.9 GB | 16 GB+ | 32 |