4-bit Open on Hugging Face
Parameters
9.4B
Weights (est.)
≈ 6.0 GB
Mac memory (est.)
16 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/flux-3-image-klein-pup-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- black-forest-labs/flux-3-image-klein-pup (quantized)
- Vendor
- black-forest-labs
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 465 in the last 30 days · 465 all time · 0 likes
- Published
- 2026-10-18 · updated 2026-10-18 (24d ago)
- Languages
- en
- Tags
- qwen3_5, apple-silicon, prompt-upsampling, prompt-rewriting, text-to-image, image-editing, flux, flux-3
Other MLX builds of black-forest-labs/flux-3-image-klein-pup
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| flux-3-image-klein-pup-4bit (this one) | 4-bit | ≈ 6.0 GB | 16 GB+ | 465 |
| flux-3-image-klein-pup-8bit | 8-bit | ≈ 10.4 GB | 16 GB+ | 403 |
| flux-3-image-klein-pup-bf16 | bf16 | ≈ 18.8 GB | 24 GB+ | 430 |