flux1-kontext-dev-fp8-e4m3fn
flux1-kontext-dev-fp8-e4m3fn
V1.0

- Base Model: FLUX.1-Kontext-dev (diffusion model component)
- Quantization: Per-tensor dynamic quantization to FP8 (E4M3FN/E5M2)
- Size Reduction: ~40% smaller than original weights
- Model Scope: This is only the diffusion_model component (not full pipeline), should be placed in ComfyUI's
diffusion_modelsdirectory
P8-quantized weights for FLUX.1-Kontext-dev diffusion models. Supports both E4M3FN and E5M2 formats.
Model Overview
This model is sourced from an external transfer (transfer address: https://huggingface.co/6chan/flux1-kontext-dev-fp8 ),if the original author has objections to this transfer, you can click,
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's requestModel Information
Active
Original author:
Chan Faych
Model Type:
Unet
Basic Model:
F1基础-Kontext
Trigger Words:
ComfyUI (with PyTorch 2.4+ and CUDA 12.4+)
Resource Name:
models/unet/flux1-kontext-dev-fp8-e4m3fn.safetensors
MD5:
6c2b535ad82f96a7ebc7240ad3017193
- Base Model: FLUX.1-Kontext-dev (diffusion model component)
- Quantization: Per-tensor dynamic quantization to FP8 (E4M3FN/E5M2)
- Size Reduction: ~40% smaller than original weights
- Model Scope: This is only the diffusion_model component (not full pipeline), should be placed in ComfyUI's
diffusion_modelsdirectory
P8-quantized weights for FLUX.1-Kontext-dev diffusion models. Supports both E4M3FN and E5M2 formats.
Model Overview
This model is sourced from an external transfer (transfer address: https://huggingface.co/6chan/flux1-kontext-dev-fp8 ),if the original author has objections to this transfer, you can click,
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request