Text-to-Image
Diffusers
Safetensors
English
Flux2KleinPipeline
image-generation
image-editing
flux
flux2
Flux2KleinPipeline
sdnq
4-bit precision
uint4
quantized
Instructions to use WaveCut/FLUX.2-klein-9B-SDNQ-uint4-static with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/FLUX.2-klein-9B-SDNQ-uint4-static with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/FLUX.2-klein-9B-SDNQ-uint4-static", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| { | |
| "base_model": "/workspace/flux2-sdnq-lab/models/flux2-klein-9b-base", | |
| "finished_at": "2026-05-14T10:11:48Z", | |
| "gpu_peak_mb": 9849, | |
| "maxrss_mb": 38230.0234375, | |
| "quantize_seconds": 13.537634736858308, | |
| "started_at": "2026-05-14T10:11:34Z", | |
| "variant": { | |
| "dequantize_fp32": false, | |
| "dynamic_loss_threshold": null, | |
| "group_size": 0, | |
| "name": "uint4-static", | |
| "quantized_matmul_dtype": null, | |
| "svd_rank": 32, | |
| "svd_steps": 8, | |
| "use_dynamic_quantization": false, | |
| "use_quantized_matmul": false, | |
| "use_stochastic_rounding": false, | |
| "use_svd": false, | |
| "weights_dtype": "uint4" | |
| } | |
| } |