Skip to content

DeepSeek-V4-Flash-5bit

mlx-community/DeepSeek-V4-Flash-5bit
5-bit Open on Hugging Face
Parameters
284B
Weights (est.)
≈ 196 GB
Mac memory (est.)
256 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-5bit --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
5-bit
Licence
—
Downloads
68 in the last 30 days · 5.8K all time · 0 likes
Published
2026-04-24 · updated 2026-04-25 (6mo ago)
Languages
en
Tags
deepseek_v4