FLUX

1 alias · FLUX.2 klein 4B, mflux 4-bit. The smallest image model in the catalog — the lightest entry point to local image generation.

Black Forest Labs' FLUX.2 klein in its 4B form, converted to mflux 4-bit: a 4.6 GB download that renders on a 12 GB Mac — the smallest image model in the catalog. Same OpenAI-compatible /v1/images/generations endpoint, same desktop Images tab support as the rest of the lane.

family

FLUX (Black Forest Labs)

aliases

1

install

pip install 'rapid-mlx[image]'

OpenAI base URL

http://localhost:8000/v1

Usage

rapid-mlx serve flux2-klein-4b

curl http://localhost:8000/v1/images/generations \
  -H 'Content-Type: application/json' \
  -d '{"model":"flux2-klein-4b","prompt":"a paper crane on wet slate, studio light","size":"1024x1024"}'

Download

Mirrored on the rapid-mlx CDN — our fresh-install test measured pulls at 90 MB/s, with automatic mid-pull fallback to Hugging Face if a mirror file slows down. One command, no account:

FLUX.2 klein 4B · 4.6 GB · mirrored ✓ · live status

Weights land in the standard Hugging Face cache, and rapid-mlx serve pulls automatically on first use.

Aliases

Frequently asked questions

Can I run FLUX locally on a Mac?

Yes — flux2-klein-4b renders entirely on Apple Silicon through POST /v1/images/generations. 4.6 GB download, 12 GB Mac.

Which Mac do I need for FLUX.2 klein?

12 GB of unified memory — the lightest entry point to local image generation on rapid-mlx.

Where next