Image models · rednote (FireRed Team)

FireRed-Image-Edit 1.1

Name: FireRed-Image-Edit 1.1
Author: rednote (FireRed Team)

Backbone: 20.4B
Native output: 1024×1024
Default steps: 40
License: apache-2.0
Released: 2026-03

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/FireRedTeam/FireRed-Image-Edit-1.1-ComfyUI (opens in a new tab)

Original weights · Hugging Face

Full-precision files from rednote (FireRed Team), for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/FireRedTeam/FireRed-Image-Edit-1.1 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from rednote (FireRed Team). The weights themselves download from Hugging Face.

github.com/FireRedTeam/FireRed-Image-Edit (opens in a new tab)

git clone https://github.com/FireRedTeam/FireRed-Image-Edit

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

Apps that run FireRed-Image-Edit 1.1

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`	61.2 GB	44.6 GB	17.8 GB	Original weights (opens in a new tab)
`FP8`	32.5 GB	24.2 GB	10.7 GB	Original weights (opens in a new tab)
`Q8 GGUF`	33.9 GB	25.6 GB	11.2 GB	GGUF (opens in a new tab)
`Q4 GGUF`	24.3 GB	16.0 GB	7.8 GB	GGUF (opens in a new tab)

Components

Backbone: 20.43B
VAE: 0.127B
Qwen2.5-VL 7B: 8.29B

Best hardware for FireRed-Image-Edit 1.1

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at Q4 GGUF.

Quality	Hardware	Quant	Memory	Speed	Runs
87Excellent quality (A+) · 87 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`FP16`	61.2 GB / 96.0 GB	59 s	Slow
80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`Q4 GGUF`	24.3 GB / 32.0 GB	80 s	Slow
80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`Q4 GGUF`	16.0 GB / 24.0 GB	1.7 min	Slowencoder in RAM
80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`Q4 GGUF`	16.0 GB / 24.0 GB	1.9 min	Slowencoder in RAM
85Excellent quality (A+) · 85 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`FP8`	10.7 GB / 16.0 GB	2.1 min	SlowCPU offload
85Excellent quality (A+) · 85 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`FP8`	10.7 GB / 16.0 GB	2.1 min	SlowCPU offload
85Excellent quality (A+) · 85 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`FP8`	10.7 GB / 16.0 GB	2.2 min	SlowCPU offload
87Excellent quality (A+) · 87 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 80GB SXM	`FP16`	61.2 GB / 80.0 GB	56 s	Slow
87Excellent quality (A+) · 87 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H800 80GB SXM	`FP16`	61.2 GB / 80.0 GB	56 s	Slow
87Excellent quality (A+) · 87 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 NVL	`FP16`	61.2 GB / 94.0 GB	60 s	Slow

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.