ComfyPilotComfyPilot
模型库 / 整模型 / MOSS-Image SFT Mixed INT8/W4 Quants
MOSS-Image SFT Mixed INT8/W4 Quants

MOSS-Image SFT Mixed INT8/W4 Quants

3054887

整模型 54 次下载 6 喜欢 更新于 2026-11-17

底模:MOSS Image

mossint4int8int

下载模型 在源站打开

文件清单 线路:原始(huggingface.co) · 切换

下载后放进对应的 ComfyUI 目录。models/ 指 ComfyUI 的模型根目录。

权重 moss_image_sft_int8_mixed.safetensors 3.7 GB 下载

说明

MOSS-Image SFT Mixed INT8/W4 Quants

作者:BakaPotatoLord

Quantization of MOSS-Image SFT aiming to reduce storage and RAM/VRAM.

This version uses a mix of INT8 and 4-bit weights and takes up approximately 3.72 GiB. It was created by testing different precision settings against the official INT8 model.

  • 107 layers use INT4 — W4A4 ConvRot MSE.
  • 61 layers use INT8 — the original INT8 ConvRot weights.

Workflow in image uses Lodestone's 8 Step Lora so my GPU won't scream for mercy

Tested on:

  • NVIDIA GTX 1660 Super 6 GB
  • 32 GB System RAM

Test settings:

  • 8/12 steps
  • CFG 1
  • Euler / Simple
  • 696 × 1048 resolution
  • Approximately 5.7 s/it on a GTX 1660 Super

示例图