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/Qwythos-27B-v1-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- empero-ai/Qwythos-27B-v1 (quantized)
- Vendor
- empero-ai
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 306 in the last 30 days · 1.2K all time · 2 likes
- Published
- 2026-08-03 · updated 2026-10-30 (12d ago)
- Languages
- en
- Tags
- qwen3_5, optiq, quantized, 4bit, mixed-precision, qwen3.5, reasoning, multimodal, vision, long-context, 1M-context, multi-token-prediction