Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Can the RTX 4090 24 GB run Qwen-Image?

Image model · 20B24 GB GDDR6X · 384-bit · 1008 GB/s · Ada LovelaceData 2026-09-25
Runs well
Yes — and comfortably.

Download FP8 (20.4 GB). With the model's working memory it needs about 23.2 GB, leaving 0.8 GB spare on 24 GB. Quality: practically identical to the original.

Best fileFP8
File size20.4 GB
VRAM needed~23.2 GB
System RAM48 GB+
Memory map · RTX 4090 24 GB23.2 GB / 24 GB
012 GB24 GB
Weights FP8 · 20.4 GBWorking memory · 2.0 GBReserve · 0.8 GBFree · 0.8 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
Modelqwen_image_fp8_e4m3fn.safetensors
FP8 · Comfy-Org/Qwen-Image_ComfyUI
models/diffusion_models20.4 GBDownload →
Text encoderqwen_2.5_vl_7b_fp8_scaled.safetensors
Qwen2.5-VL 7B FP8 · Comfy-Org/Qwen-Image_ComfyUI
models/text_encoders9.4 GBDownload →
VAEqwen_image_vae.safetensors
Qwen-Image VAE · Comfy-Org/Qwen-Image_ComfyUI
models/vae0.3 GBDownload →
Total download · keep about the same free on disk30.1 GB

Alternatives: Qwen2.5-VL 7B BF16 (16.6 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

System RAM: 48 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 30.1 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 36.1 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every Qwen-Image file on 24 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
40.9 GB43.7 GB19.7 GB too bigthe original weightsHugging Face →
FP8 ←
SAFETENSORS · Comfy-Org
20.4 GB23.2 GBfits · 0.8 GB sparepractically identical to the originalHugging Face →
Q8_0
GGUF · city96
21.8 GB24.6 GBspills 0.6 GBpractically identical to the originalHugging Face →
Q6_K
GGUF · city96
16.8 GB19.6 GBfits · 4.4 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · city96
14.9 GB17.7 GBfits · 6.3 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · city96
13.1 GB15.9 GBfits · 8.1 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · city96
9.7 GB12.5 GBfits · 11.5 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · city96
7.1 GB9.9 GBfits · 14.1 GB spareheavy loss; a last resortHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 2 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

Qwen2.5-VL 7B: 16.6 GB as 16-bit, 9.4 GB as FP8. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 24 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

The RTX 4090 24 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)

RTX 4090 24 GB: 24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. Everything that runs on the RTX 4090 24 GB →

05What more VRAM would change

Nothing to gain for this model: the RTX 4090 24 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.

What changes from the RTX 4090 24 GB to the RTX 5090 32 GB →

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Qwen-Image on a RTX 4090 24 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does Qwen-Image need?

Around 9.9 GB with the smallest file (Q2_K) and 23.2 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 43.7 GB.

Which Qwen-Image file should I download for the RTX 4090 24 GB?

FP8 (20.4 GB) from Comfy-Org/Qwen-Image_ComfyUI.

Is FP8 faster than GGUF on the RTX 4090 24 GB?

It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.

How much do I need to download for Qwen-Image on the RTX 4090 24 GB?

About 30.1 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 24 GB card, 48 GB of system RAM or more is recommended.