4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 16.1 GB
Mac memory (est.)
24 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/Qwopus3.5-27B-v3-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Jackrong/Qwopus3.5-27B-v3 (adapter)
- Vendor
- Jackrong
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 31 in the last 30 days · 980 all time · 1 likes
- Published
- 2026-04-05 · updated 2026-04-05 (7mo ago)
- Languages
- en, zh, ko
- Tags
- qwen3_5, unsloth, qwen, qwen3.5, reasoning, chain-of-thought, lora, competitive-programming