flux2-klein-4b-int4-ov

OpenVINO IR export of black-forest-labs/FLUX.2-klein-4B, quantized to INT4 — 4347 MB.


Quantization	weight compression, group 64 (transformer + text encoder); VAE stays INT8
Lesson	07 FLUX.2 Klein image generation
Built by	`convert/convert_all.py` of the ARCademy OpenVINO courseware

Distilled: 4 steps, guidance_scale 1.0. The same folder serves Text2ImagePipeline and Image2ImagePipeline (strength≈0.9).

from huggingface_hub import snapshot_download
model_dir = snapshot_download("circulus/flux2-klein-4b-int4-ov")

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for circulus/flux2-klein-4b-int4-ov

Base model

Finetuned

(57)

this model