4-bit Open on Hugging Face
Parameters
125B
Weights (est.)
≈ 71.1 GB
Mac memory (est.)
96 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/Qwen3.5-122B-A10B-oQ4-mtp --image photo.jpg --prompt "Describe this image"
Details
- Base model
- —
- Vendor
- —
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 258 in the last 30 days · 4.9K all time · 4 likes
- Published
- 2026-05-27 · updated 2026-05-28 (5mo ago)
- Tags
- qwen3_5_moe