Skip to content

deepseek-vl2-small-bf16

mlx-community/deepseek-vl2-small-bf16
Vision + text · transformers
bf16 Open on Hugging Face
Parameters
16B
Weights (est.)
≈ 32.3 GB
Mac memory (est.)
48 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-small-bf16 --image photo.jpg --prompt "Describe this image"

Details

Base model
—
Vendor
—
Task
Vision + text
Quantisation
bf16
Licence
deepseek
Downloads
83 in the last 30 days · 522 all time · 0 likes
Published
2024-12-22 · updated 2024-12-22 (1y ago)
Tags
deepseek_vl_v2