---
license: other
license_name: flux-non-commercial-license
base_model:
  - black-forest-labs/FLUX.2-dev
base_model_relation: quantized
tags:
  - diffusion-single-file
  - comfyui
  - image-generation
  - image-editing
  - flux
---

A FLUX.2-dev model quantized to INT8 with ConvRot using a conservative quantization policy.

On my potato machine, in T2I without using distilled LoRA, int8-convrot-aggressive is 20 seconds faster than int8-convrot. Neither model produced images that deviated from bf16.

T2I Example:
<img src="ComparisonA.webp" width="1000">
<img src="ComparisonB.webp" width="1000">
Image Edit Example:
<img src="ComparisonC.webp" width="1000">
<img src="ComparisonD.webp" width="1000">