# city96/ComfyUI-GGUF

GGUF Quantization support for native ComfyUI models

Repository: https://github.com/city96/ComfyUI-GGUF
Canonical: https://ross.abutalabs.com/products/comfyui-gguf
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-01-12T13:02:18+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 62, release rhythm 35, longevity 53
- inputs: {"age_days": 748, "days_push": 233, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3953, forks 364 (observed 2026-08-28T04:08:30.472809+00:00)

## What it is
A ComfyUI custom node pack that adds GGUF quantization support for loading diffusion models like FLUX and Stable Diffusion 3.5 in low-bitrate quantized formats. It enables running large transformer-based image models on low-end GPUs with reduced VRAM usage.

## Use cases
- run FLUX.1 on a low-VRAM GPU with GGUF quantization
- load quantized Stable Diffusion 3.5 models in ComfyUI
- reduce VRAM usage when generating images with diffusion models
- load a quantized T5 text encoder in ComfyUI
- use GGUF model files with the ComfyUI Unet loader
- generate images with variable bitrate quantized DiT models

## When to choose
- you use ComfyUI and want to run large diffusion models on limited GPU memory
- you have pre-quantized GGUF versions of FLUX or SD3.5 models
- you want to quantize the T5 text encoder to save additional VRAM

## When to avoid
- you need quantization for conv2d-based UNET models, which is not supported
- you don't use ComfyUI for image generation
- you need fully stable LoRA support, which is still experimental

## Facets
- artifact type: plugin
- maturity: active
- function: llm-inference, machine-learning, image-processing, plugin-system
- domain: machine-learning, image-processing, developer-tools
- platform: python, cross-platform
- tags: comfyui, gguf, quantization, stable-diffusion, flux, diffusion-models, vram-optimization, custom-nodes, gpu

## Member repositories
- city96/ComfyUI-GGUF (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.472809+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:31.011935+00:00, confidence not recorded.
  - readme: https://github.com/city96/ComfyUI-GGUF (fetched 2026-08-28T04:08:30.472809+00:00, sha c5cf6641b3c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.