Skip to content

deepseek-vl-1.3b-chat-8bit

mlx-community/deepseek-vl-1.3b-chat-8bit
8-bit Open on Hugging Face
Parameters
2.0B
Weights (est.)
≈ 2.1 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-vl-1.3b-chat-8bit --image photo.jpg --prompt "Describe this image"

Details

Base model
—
Vendor
—
Task
Vision + text
Quantisation
8-bit
Licence
deepseek
Downloads
95 in the last 30 days · 800 all time · 1 likes
Published
2024-07-26 · updated 2024-12-26 (1y ago)
Tags
multi_modality