8-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 29.5 GB
Mac memory (est.)
48 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/Qwen3.5-27B-heretic-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- coder3101/Qwen3.5-27B-heretic (quantized)
- Vendor
- coder3101
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 157 in the last 30 days · 14K all time · 8 likes
- Published
- 2026-02-26 · updated 2026-02-26 (8mo ago)
- Tags
- qwen3_5, quantized, 8bit, vision, qwen3.5, abliterated, uncensored