Instructions to use eduardoabreu81/iris-z-small-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use eduardoabreu81/iris-z-small-quantized with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Iris-Z-small, quantized
INT8 ConvRot and W4A8 builds of Iris-Z-small by SperidLabs - one model that paints images, reads their depth, and repaints a scene from its depth, built on FLUX.2 [klein] 9B.
Made for Forge Neo with the Iris-Z for Forge Neo extension.
| File | Format | Size | Picture vs bf16 | Depth vs bf16 |
|---|---|---|---|---|
iris-z-small_int8_convrot.safetensors |
INT8 ConvRot | 9.4 GB | 26.7 dB | 40.1 dB |
iris-z-small_w4a8.safetensors |
W4A8 | 5.6 GB | 22.7 dB | 32.8 dB |
| original bf16 (speridlabs/iris-z) | bf16 | 18.2 GB | - | - |
PSNR against the bf16 checkpoint, same prompt and seed, 1024x1024, 50 steps.

What was quantized
Only the 112 linear layers of the 8 double and 24 single transformer blocks, as in the published FLUX.2 [klein] 9B INT8 ConvRot builds. The input and output layers, the timestep embedder, the stream modulations and Iris-Z's modality_in stay in bf16. Both files hold the diffusion model only - the text encoder and VAE are separate.
Quantized with Merge Studio (FLUX.2 profile).
- INT8 ConvRot is the closest to the original.
- W4A8 is the smallest, and runs at full speed on RTX 30 series cards or newer - on older cards choose INT8.
How to use
- Install the Iris-Z for Forge Neo extension in Forge Neo
- Put one of these files in
models/Stable-diffusion - Add the Qwen3 8B text encoder (
qwen_3_8borqwen_3_8b_fp8mixed) tomodels/text_encoderand the FLUX.2 VAE (flux2-vae) tomodels/VAE - Pick the iris_z UI preset - Euler, Flux2 schedule, 50 steps, CFG 4
Everything Iris-Z-small does works with both files:


Credits
- Iris-Z by SperidLabs - the model (paper, code)
- FLUX.2 by Black Forest Labs - the model Iris-Z is built on
License
The weights are derived from FLUX.2 and Iris-Z and stay under the FLUX Non-Commercial License, as the original Iris-Z weights.
Made with ❤️ for the Stable Diffusion community
- Downloads last month
- 616