Skip to content

DeepSeek-V4-Flash-bf16

mlx-community/DeepSeek-V4-Flash-bf16
bf16 Open on Hugging Face
Parameters
284B
Weights (est.)
≈ 1123 GB
Mac memory (est.)
> 512 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-bf16 --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
bf16
Licence
—
Downloads
162 in the last 30 days · 8.6K all time · 2 likes
Published
2026-04-24 · updated 2026-04-25 (6mo ago)
Languages
en
Tags
deepseek_v4