Skip to content

DeepSeek-V4-Flash-mxfp4

mlx-community/DeepSeek-V4-Flash-mxfp4
MXFP4 Open on Hugging Face
Parameters
284B
Weights (est.)
≈ 160 GB
Mac memory (est.)
192 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-lm on an Apple silicon Mac:

pip install mlx-lmmlx_lm.generate --model mlx-community/DeepSeek-V4-Flash-mxfp4 --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
MXFP4
Licence
—
Downloads
93 in the last 30 days · 6.9K all time · 1 likes
Published
2026-04-24 · updated 2026-04-25 (6mo ago)
Languages
en
Tags
deepseek_v4