FLUX.2-klein-4B
A 3.9B parameter image to image model from Black Forest Labs, with 7 MLX builds, from 4-bit to 8-bit and Apple Core AI export recipes.
- Parameters
- 3.9B From Hugging Face
- Quantisation
- 4-bit FLUX.2-Klein-4B-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 17K This build, last 30 days
- Task
- Image to image Image
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 3.9B From Hugging Face
- Compression
- 4-bit Apple’s preset
- Memory needed
- 5 GB Estimate from parameters
- Context
- — Fixed at export
- Precision
- FP16 Compute precision
- Platforms
- Not stated Not stated
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 8 Jun 2026 First registry commit
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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.2-Klein-4B-4bitMemory
Estimated from the parameter count at Apple’s compression setting. Apple does not publish package sizes.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.diffusion.export flux2-klein-4b
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
7 on mlx-community| FLUX.2-Klein-4B-4bit | 4-bit | — | — | 17K |
|---|---|---|---|---|
| FLUX.2-Klein-4B-3bit | 3-bit | — | — | 719 |
| FLUX.2-Klein-4B-6bit | 6-bit | — | — | 114 |
| FLUX.2-Klein-4B-5bit | 5-bit | — | — | 62 |
| FLUX.2-klein-4B-bf16 | bf16 | — | — | 0 |
| flux2-klein-4b-4bit | 4-bit | — | — | 0 |
| flux2-klein-4b-8bit | 8-bit | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| flux2-klein-4b 4bit recommended; use --compression none for full precision |
Any | 4-bit | FP16 | — |