README.md

---
pipeline_tag: text-to-image
base_model:
- krea/Krea-2-Turbo
base_model_relation: quantized
language:
- en
library_name: diffusers
license: other
license_name: krea-2-community-license
license_link: https://huggingface.co/krea/Krea-2-Turbo/resolve/main/LICENSE.pdf
tags:
 - nvfp4
 - quantization
---

# Krea2-Turbo-mixed-NVFP4
Mixed 8-bit microscaling quantization of [Krea-2-Turbo](https://huggingface.co/krea/Krea-2-Turbo), generated with [`convert_to_quant`](https://github.com/silveroxides/convert_to_quant).

* **Format**: Mixed NFVP4 and MXFP8 with some layers preserved as BF16.
* **Size**: 8.8G GB (−66% vs BF16).
* **Inference**: ComfyUI + [`comfy-kitchen`](https://github.com/Comfy-Org/comfy-kitchen), Blackwell GPU (RTX 50xx / B100 / B200).

<table>
  <tr>
    <td align="center">
      <a href="Krea2-Turbo-mixed-NVFP4/blob/main/assets/nvfp4.png"><img src="assets/nvfp4.png" style="width: 66%; height: auto;"></a>
    </td>
    <td align="center">
      <a href="Krea2-Turbo-mixed-NVFP4/blob/main/assets/bf16.png"><img src="assets/bf16.png" style="width: 66%; height: auto;"></a>
    </td>
  </tr>
  <tr>
    <td align="center"><strong>NVFP4</strong></td>
    <td align="center"><strong>BF16</strong></td>
  </tr>
</table>

## Quantization
The model weights have been partially quantized to **NVFP4** (NVIDIA Floating Point 4-bit) and **MXFP8**, quantization formats supported on NVIDIA Blackwell architecture GPUs.

The following `convert_to_quant` parameters where used. This conversion takes about 1 hour on an RTX 5060 TI.
```bash
$ convert_to_quant -i krea2_turbo_bf16.safetensors \
    --nvfp4 \
    --krea2 \
    --comfy_quant \
    --save-quant-metadata \
    --custom-type mxfp8 \
    --custom-layers \
      "blocks\.(0|1|2|24|25|26)\.attn\.(wq|wk|wv|wo)\.weight|blocks\.(0|1|2|25|26|27)\.attn\.gate\.weight|blocks\.(0|1|2|3|25|26|27)\.mlp\.gate\.weight|txtfusion\.layerwise_blocks\.(0|1)\.attn\.(wq|wk|wv|wo|gate)\.weight|txtfusion\.layerwise_blocks\.(0|1)\.mlp\.gate\.weight|txtfusion\.refiner_blocks\.(0|1)\.attn\.(wq|wk|wv|gate)\.weight|txtfusion\.refiner_blocks\.(0|1)\.mlp\.(gate|up)\.weight|txtfusion\.refiner_blocks\.0\.mlp\.down\.weight" \
    --exclude-layers \
      "blocks\.27\.attn\.(wq|wk|wv)\.weight|txtfusion\.refiner_blocks\.(0|1)\.attn\.wo\.weight|txtfusion\.refiner_blocks\.1\.mlp\.down\.weight" \
    --num-iter 4000 \
    --top-p 0.35 \
    --calib-samples 8192 \
    --scale-optimization iterative \
    --scale-refinement 2 \
    --extract-lora \
    --lora-rank 64 \
    --lora-target "attn\.(wo|gate)\.weight|mlp\.(gate|down)\.weight" \
    -o krea2_turbo_mixed_nvfp4.safetensors
```