4-bit Open on Hugging Face
Parameters
9.0B
Weights (est.)
≈ 6.0 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/LensVLM-9B-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- apple/LensVLM-9B (quantized)
- Vendor
- apple
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apple-amlr
- Downloads
- 360 in the last 30 days · 1.2K all time · 5 likes
- Published
- 2026-09-24 · updated 2026-10-18 (24d ago)
- Tags
- qwen3_5, optiq, quantized, mixed-precision, 4bit, 8bit, qwen3.5, vision-language-model, long-context, visual-text-compression, apple-silicon