CO

ComfyUI Model Backups

ComfyuiGGUF by AEmotionStudioUpdated 2026-06-26
Download on Hugging Face
Parameters7.62B
Context512
Layers24
Architecturet5encoder
Smallest quant3.4 GB
Quick answer

ComfyUI Model Backups needs about 11.8 GB of memory at Q8_0 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 3.4 GB (Q5_K_M) to 10.4 GB (Q4_K_S).

ComfyUI Model Backups – a collection of backup weight files

ComfyUI Model Backups is a repository of weight files for ComfyUI models. The collection includes 21 quantized files with various GGUF formats. The models are based on a t5encoder architecture with 7.62 billion parameters.

Good at

  • Backup and restore of ComfyUI models
  • Organized by model type
  • Supports tools ability

Limits

  • No vision support
  • License is other
  • No trained context beyond 512 tokens

Best for

  • Restoring missing ComfyUI model types
  • Managing local model backups
  • Testing quantized weights

Who it’s for. Users who maintain ComfyUI installations and need reliable backups of model weights. It is also useful for developers who want to experiment with different quantizations of the same model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M3.4 GB 4.1 GB
Fits Get file →
Q2_K5.3 GB 6.0 GB
Fits Get file →
Q2_K5.3 GB 6.0 GB
Fits Get file →
Q8_06.0 GB 6.7 GB
Fits Get file →
Q3_K_S6.5 GB 7.2 GB
Tight Get file →
Q3_K_S6.5 GB 7.2 GB
Tight Get file →
Q3_K_M7.2 GB 7.9 GB
Tight Get file →
Q3_K_M7.2 GB 7.9 GB
Tight Get file →
Q3_K_M7.2 GB 7.9 GB
Tight Get file →
Q3_K_M7.2 GB 7.9 GB
Tight Get file →
Q8_08.1 GB 8.8 GB
Too big Get file →
Q4_K_S8.7 GB 9.4 GB
Too big Get file →
Q4_K_S8.7 GB 9.4 GB
Too big Get file →
Q3_K_S9.0 GB 9.7 GB
Too big Get file →
—9.6 GB 10.4 GB
Too big Get file →
—9.6 GB 10.4 GB
Too big Get file →
—9.7 GB 10.4 GB
Too big Get file →
—9.7 GB 10.4 GB
Too big Get file →
Q4_K_S10.0 GB 10.7 GB
Too big Get file →
Q4_K_S10.4 GB 11.1 GB
Too big Get file →
Q4_K_S10.4 GB 11.1 GB
Too big Get file →

For 8 GB VRAM, the Q5_K_M file (3.39 GB, 7.1 GB memory at 8k context) is a good choice. If more VRAM is available, Q8_0 (6.04 GB, 9.8 GB memory) provides higher precision. For very limited memory, Q2_K (5.3 GB, 9 GB memory) is the smallest option.

What GPU do you need for ComfyUI Model Backups?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (3.4 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (10.4 GB file, about 14.2 GB in use).

Which ComfyUI Model Backups quant should you choose?

Q8_0 (8.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q5_K_M at 3.4 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturet5encoder
Parameters7.62B
Layers24
Trained context512 tokens
KV cache (fp16)384 KB per token

Source

Quantized byAEmotionStudio
FamilyComfyui
Licenseother
Downloads (HF)927
Last updated2026-06-26

Frequently asked questions about ComfyUI Model Backups

How much VRAM does ComfyUI Model Backups need?

About 11.8 GB at Q8_0 with an 8K context window. That is the 8.1 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 ComfyUI Model Backups on an 8 GB GPU?

Yes, with Q5_K_M: the 3.4 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ComfyUI Model Backups GGUF?

It depends on the quant: Q5_K_M is 3.4 GB, Q2_K is 5.3 GB, Q2_K is 5.3 GB, Q8_0 is 6.0 GB, Q3_K_S is 6.5 GB, Q3_K_S is 6.5 GB and 15 more.

What context length does ComfyUI Model Backups support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 3.2 GB at 8K and 0.2 GB at 512.

Where can I download ComfyUI Model Backups GGUF?

The files are on Hugging Face in the AEmotionStudio/ComfyUI-Model-Backups repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ComfyUI Model Backups use?

Hugging Face lists the license as other. 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 Q5_K_M on 8 GB VRAM?

Yes, Q5_K_M requires 7.1 GB memory at 8k context, which fits within 8 GB VRAM.

What is the largest quant file I can use with 12 GB VRAM?

Q4_K_S requires 14.2 GB memory, so it would exceed 12 GB. The largest fitting file is Q8_0 at 9.8 GB memory.

Does this collection include vision models?

No, the collection is limited to t5encoder models and does not include vision support.

Similar models

Browse all →

More from AEmotionStudio

All by AEmotionStudio →

More Comfyui models

All Comfyui →

Other small models

All small models →