6-bit Open on Hugging Face
Parameters
9.4B
Weights (est.)
≈ 8.2 GB
Mac memory (est.)
16 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/lift-oQ6 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- datalab-to/lift (quantized)
- Vendor
- datalab-to
- Task
- Vision + text
- Quantisation
- 6-bit
- Licence
- openrail
- Downloads
- 20 in the last 30 days · 84 all time · 0 likes
- Published
- 2026-06-27 · updated 2026-06-27 (4mo ago)
- Tags
- qwen3_5, extraction, structured-data, json, mlx-vlm, quantized