Downloads · 30 days
0
flux2-klein-4b-ov
Nekodeus/flux2-klein-4b-ov
flux2-klein-4b-ov is a text-to-image model from Nekodeus. Use it when you need an image from a text prompt. It is set up for openvino. The card lists the license as apache-2.0.
OpenVINO IR (INT8) conversion of black-forest-labs/FLUX.2-klein-base-4B (4B rectified-flow transformer + text encoder + VAE). Standard diffusers layout verified before conversion.
Access
Public
Updated Sep 22, 2026
Repo size
8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin8 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- openvino
- License
- apache-2.0
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 22, 2026
- SHA
- 74818362
Model card
From the Hugging Face model README
FLUX.2-klein-base-4B — OpenVINO INT8
OpenVINO IR (INT8) conversion of black-forest-labs/FLUX.2-klein-base-4B (4B rectified-flow transformer + text encoder + VAE). Standard diffusers layout verified before conversion.
Why OpenVINO?
- Runs on any CPU with no CUDA/NVIDIA dependency, plus GPU acceleration where available (AMD, Nvidia, Intel) — no vendor-locked passes used
- Full pipeline is ~8GB, deployable on 8GB VRAM cards
Deployment note (8GB cards)
Transformer (~3.9GB INT8) runs on GPU; the text encoder runs once per prompt
and can sit on CPU via AUTO/explicit device placement, leaving comfortable
headroom on 8GB cards.
Conversion
| Parameter | Value |
|---|---|
| Tool | optimum-cli export openvino --weight-format int8 --all-layers (device-neutral) |
| Precision | INT8 |
| Source | black-forest-labs/FLUX.2-klein-base-4B |
| Verified | transformer, text_encoder, vae_encoder, vae_decoder all load in ov.Core on Kaggle GPU |
Usage (any device)
import openvino as ov
core = ov.Core()
compiled = core.compile_model(core.read_model("transformer/openvino_model.xml"), "AUTO")
- Task
- Text-to-Image
- Library
- openvino
- License
- apache-2.0
- Languages
- en
- Created
- Sep 20, 2026
- Updated
- Sep 22, 2026