4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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.
Details
- Base model
- black-forest-labs/FLUX.2-klein-4B (finetune)
- Vendor
- black-forest-labs
- Task
- Image to image
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 7.2K in the last 30 days · 18K all time · 3 likes
- Published
- 2026-05-29 · updated 2026-05-29 (5mo ago)
- Languages
- en
- Tags
- diffusion-single-file, text-to-image, image-editing, flux
Other MLX builds of black-forest-labs/FLUX.2-klein-4B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| FLUX.2-Klein-4B-4bit (this one) | 4-bit | — | — | 7.2K |
| FLUX.2-Klein-4B-3bit | 3-bit | — | — | 708 |
| FLUX.2-Klein-4B-6bit | 6-bit | — | — | 114 |
| FLUX.2-Klein-4B-5bit | 5-bit | — | — | 60 |
| flux2-klein-4b-4bit | 4-bit | — | — | 0 |
| flux2-klein-4b-8bit | 8-bit | — | — | 0 |
| FLUX.2-klein-4B-bf16 | bf16 | — | — | 0 |