Skip to content

deepseek-vl2-tiny-6bit

mlx-community/deepseek-vl2-tiny-6bit
Vision + text · transformers
6-bit Open on Hugging Face
Parameters
3.4B
Weights (est.)
≈ 2.9 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/deepseek-vl2-tiny-6bit --image photo.jpg --prompt "Describe this image"

Details

Base model
—
Vendor
—
Task
Vision + text
Quantisation
6-bit
Licence
deepseek
Downloads
91 in the last 30 days · 987 all time · 1 likes
Published
2024-12-22 · updated 2024-12-22 (1y ago)
Tags
deepseek_vl_v2