Black Forest Labs · First MLX build 18 Oct 2026
flux-3-image-klein
MLX
Image flux-kommunity-license Gated
A 5.5B parameter image to image model from Black Forest Labs, with one MLX build at bf16.
- Parameters
- 5.5B From Hugging Face
- Quantisation
- bf16 flux-3-image-klein-bf16
- Memory needed
- 15 GB Estimate, unified memory
- Download
- 11.1 GB Weights, estimated
- Downloads
- 108 This build, last 30 days
- Task
- Image to image Image
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 15 GB at bf16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/flux-3-image-klein-bf16MLX builds
1 on mlx-community| flux-3-image-klein-bf16 Gated | bf16 | 11.1 GB | 15 GB | 108 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.