XORTRON.CriminalComputing.2026.27B.Instruct.NEXT-4.5bit-msq
mlx-community/XORTRON.CriminalComputing.2026.27B.Instruct.NEXT-4.5bit-msq
Vision + text · transformers
5-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 4.5 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.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/XORTRON.CriminalComputing.2026.27B.Instruct.NEXT-4.5bit-msq --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Qwen/Qwen3.5-27B (quantized)
- Vendor
- Qwen
- Task
- Vision + text
- Quantisation
- 5-bit
- Licence
- apache-2.0
- Downloads
- 18 in the last 30 days · 118 all time · 0 likes
- Published
- 2026-04-20 · updated 2026-04-20 (6mo ago)
- Tags
- qwen3_5, heretic, uncensored, decensored, abliterated
Other MLX builds of Qwen/Qwen3.5-27B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| XORTRON.CriminalComputing.2026.27B.Instruct.NEXT-4.5bit-msq (this one) | 5-bit | ≈ 4.5 GB | 8 GB+ | 18 |
| Qwen3.5-27B-OptiQ-4bit | 4-bit | ≈ 16.1 GB | 24 GB+ | 449 |
| Qwen3.5-27B-mxfp8 | MXFP8 | ≈ 29.5 GB | 48 GB+ | 772 |