Image models · OpenMOSS

MOSS-Image SFT

Name: MOSS-Image SFT
Author: OpenMOSS

Backbone: 5.1B
Native output: 1024×1024
Default steps: 50
License: apache-2.0
Released: 2026-10

How to run it

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/unsloth/MOSS-Image-SFT-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from OpenMOSS, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/OpenMOSS-Team/MOSS-Image-SFT (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from OpenMOSS. The weights themselves download from Hugging Face.

github.com/OpenMOSS/MOSS-Image (opens in a new tab)

git clone https://github.com/OpenMOSS/MOSS-Image

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

Apps that run MOSS-Image SFT

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Windows PC, NVIDIA GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

App	Type	Opens it as	Systems	Engine	Start
Unsloth Desktop	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
ComfyUI	Desktop app	Original or GGUF	macOSWindowsLinux	PyTorch, GGUF via ComfyUI-GGUF	Get ComfyUI
SwarmUI	Desktop app	Original or GGUF	macOSWindowsLinux	ComfyUI	Get SwarmUI
SD.Next	Desktop app	Original or GGUF	macOSWindowsLinux	PyTorch	Get SD.Next
Stability Matrix	Desktop app	Original or GGUF	macOSWindowsLinux	installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus	Get Stability Matrix

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision	Everything on GPU	Text encoder offloaded	Sequential offload	Download
`FP16`	29.3 GB	12.5 GB	5.8 GB	Original weights (opens in a new tab)
`FP8`	15.8 GB	7.4 GB	4.0 GB	Original weights (opens in a new tab)
`Q8 GGUF`	16.2 GB	7.8 GB	4.1 GB	GGUF (opens in a new tab)
`Q4 GGUF`	13.8 GB	5.4 GB	3.3 GB	GGUF (opens in a new tab)

Components

Backbone: 5.08B
VAE: 0.062B
Qwen3.5 9B: 8.39B

Best hardware for MOSS-Image SFT

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q4 GGUF.

Quality	Hardware	Quant	Memory	Speed	Runs
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`FP8`	15.8 GB / 24.0 GB	13 s	Runs great
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`FP8`	15.8 GB / 24.0 GB	14 s	Runs well
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`FP8`	15.8 GB / 32.0 GB	11 s	Runs great
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`FP8`	15.8 GB / 24.0 GB	24 s	Runs well
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`FP16`	29.3 GB / 96.0 GB	10 s	Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`FP16`	12.5 GB / 16.0 GB	20 s	Runs wellencoder in RAM
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`FP16`	12.5 GB / 16.0 GB	20 s	Runs wellencoder in RAM
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`FP16`	12.5 GB / 16.0 GB	21 s	Runs wellencoder in RAM
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4070 Ti SUPER	`FP16`	12.5 GB / 16.0 GB	24 s	Runs wellencoder in RAM
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5070 Ti	`FP16`	12.5 GB / 16.0 GB	24 s	Runs wellencoder in RAM

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.