MO

MOSS Image

MossGGUF by PALLER-NOVUSUpdated 2026-10-23
Download on Hugging Face
Parameters5.08B
Context—
Layers—
Architecture—
Smallest quant1.2 GB
Quick answer

MOSS Image needs about 3.9 GB of memory at MXFP4 (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 44 quants, from 1.2 GB (Q1_0) to 5.6 GB (Q8_0).

MOSS Image – 5.08B text‑to‑image diffusion model in GGUF format

MOSS Image is a 5.08B diffusion backbone with a separate Qwen3.5‑9B text encoder. It supports natural‑language prompts, tag sequences, and JSON layouts for controlling text placement and object arrangement. The model is released under apache‑2.0 and is available as multiple GGUF quantizations.

Good at

  • Text‑to‑image generation
  • Layout‑to‑image with JSON prompts
  • Prompt enhancement via MOSS‑Image Prompt Enhancer

Limits

  • No vision support – only text‑to‑image
  • Requires external text encoder, VAE and runtime
  • Large VRAM needed for higher‑quality quants

Best for

  • Generating detailed scene layouts
  • Creating images from structured JSON prompts
  • Enhancing prompts for local LLM agents

Who it’s for. Developers and researchers building local text‑to‑image pipelines. The model is suitable for users who have an NVIDIA GPU with CUDA support and can integrate the required text encoder and VAE. It is ideal for those who prefer open‑source diffusion models with flexible quantization options.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_01.2 GB 1.8 GB
Fits Get file →
Q1_01.2 GB 1.8 GB
Fits Get file →
TQ1_01.5 GB 2.2 GB
Fits Get file →
TQ1_01.5 GB 2.2 GB
Fits Get file →
IQ1_M1.6 GB 2.2 GB
Fits Get file →
IQ1_M1.6 GB 2.2 GB
Fits Get file →
TQ2_01.7 GB 2.5 GB
Fits Get file →
TQ2_01.7 GB 2.5 GB
Fits Get file →
Q2_01.9 GB 2.6 GB
Fits Get file →
Q2_01.9 GB 2.6 GB
Fits Get file →
IQ2_S2.0 GB 2.8 GB
Fits Get file →
IQ2_S2.0 GB 2.8 GB
Fits Get file →
Q2_K2.1 GB 2.8 GB
Fits Get file →
Q2_K2.1 GB 2.8 GB
Fits Get file →
IQ3_XXS2.3 GB 3.1 GB
Fits Get file →
IQ3_XXS2.3 GB 3.1 GB
Fits Get file →
IQ3_S2.6 GB 3.4 GB
Fits Get file →
Q3_K2.6 GB 3.4 GB
Fits Get file →
IQ3_S2.6 GB 3.4 GB
Fits Get file →
Q3_K2.6 GB 3.4 GB
Fits Get file →
MXFP43.1 GB 3.9 GB
Fits Get file →
MXFP43.1 GB 3.9 GB
Fits Get file →
IQ4_XS3.1 GB 3.9 GB
Fits Get file →
IQ4_XS3.1 GB 3.9 GB
Fits Get file →
IQ4_NL3.2 GB 4.1 GB
Fits Get file →
—3.2 GB 4.1 GB
Fits Get file →
Q4_03.2 GB 4.1 GB
Fits Get file →
IQ4_NL3.2 GB 4.1 GB
Fits Get file →
—3.2 GB 4.1 GB
Fits Get file →
Q4_03.2 GB 4.1 GB
Fits Get file →
Q4_K3.2 GB 4.1 GB
Fits Get file →
Q4_K3.2 GB 4.1 GB
Fits Get file →
Q4_13.5 GB 4.4 GB
Fits Get file →
Q4_13.5 GB 4.4 GB
Fits Get file →
Q5_03.8 GB 4.8 GB
Fits Get file →
Q5_03.8 GB 4.8 GB
Fits Get file →
Q5_K3.8 GB 4.8 GB
Fits Get file →
Q5_K3.8 GB 4.8 GB
Fits Get file →
Q5_14.1 GB 5.1 GB
Fits Get file →
Q5_14.1 GB 5.1 GB
Fits Get file →
Q6_K4.5 GB 5.5 GB
Fits Get file →
Q6_K4.5 GB 5.5 GB
Fits Get file →
Q8_05.6 GB 6.8 GB
Fits Get file →
Q8_05.6 GB 6.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K (3.22 GB, 4.1 GB memory at 8k context). For 12 GB VRAM, Q5_0 (3.82 GB, 4.8 GB memory) or Q5_K. For 16 GB VRAM, Q6_K (4.46 GB, 5.5 GB memory) or Q8_0 (5.63 GB, 6.8 GB memory). Estimates are approximate.

What GPU do you need for MOSS Image?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ4_XS (3.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (4.5 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.6 GB file, about 6.8 GB in use).

Which MOSS Image quant should you choose?

MXFP4 (3.1 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is Q1_0 at 1.2 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters5.08B

Source

Quantized byPALLER-NOVUS
FamilyMoss
Licenseapache-2.0
Downloads (HF)1,342
Last updated2026-10-23

Frequently asked questions about MOSS Image

How much VRAM does MOSS Image need?

About 3.9 GB at MXFP4 with an 8K context window. That is the 3.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run MOSS Image on an 8 GB GPU?

Yes, with Q8_0: the 5.6 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MOSS Image GGUF?

It depends on the quant: Q1_0 is 1.2 GB, Q1_0 is 1.2 GB, TQ1_0 is 1.5 GB, TQ1_0 is 1.5 GB, IQ1_M is 1.6 GB, IQ1_M is 1.6 GB and 38 more.

Where can I download MOSS Image GGUF?

The files are on Hugging Face in the PALLER-NOVUS/MOSS-Image-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MOSS Image use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run MOSS Image on 8 GB VRAM?

Yes, the Q4_K quantization requires about 4.1 GB memory at 8k context, which fits within 8 GB VRAM with headroom.

Does MOSS Image support vision input?

No, MOSS Image is a text‑to‑image model and does not accept vision input.

What license applies to MOSS Image?

The model is released under the apache‑2.0 license.

Other GGUFs of MOSS-Image-Base

Similar models

Browse all →

More from PALLER-NOVUS

All by PALLER-NOVUS →

More Moss models

All Moss →

Other small models

All small models →