MOSS-Image-SFT

Quantised media packages of OpenMOSS-Team/MOSS-Image-SFT.

MECHA Forge

MECHA — Model Engineering & Contextual Hearth Assembly

These media packages have been forged and optimized in the MECHA Forge. Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.

Available quantizations

Quant	Denoiser	Text encoder	VAE
FP8	FP8	FP8	FP8
INT8	INT8	INT8	INT8
FP4	FP4	FP8	FP8
INT4	INT4	INT8	INT8

The text encoder and VAE are shared between formats: FP4 reuses the FP8 files, INT4 reuses the INT8 files.

Files

text_encoder/qwen3.5_8b_fp8.safetensors   (FP8 and FP4)
text_encoder/qwen3.5_8b_int8.safetensors  (INT8 and INT4)
transformer/moss_image_sft_fp4.safetensors
transformer/moss_image_sft_fp8.safetensors
transformer/moss_image_sft_int4.safetensors
transformer/moss_image_sft_int8.safetensors
vae/moss_image_sft_vae_fp8.safetensors   (FP8 and FP4)
vae/moss_image_sft_vae_int8.safetensors  (INT8 and INT4)