Check my GPU →

Can the RTX 3090 24 GB run Ming-Image 0.1 Design?

Yes. 16-bit fits on the RTX 3090 24 GB with 9.4 GB to spare.

Image model · 6.15B24 GB GDDR6X · 384-bit · 936 GB/s · AmpereData 2026-10-01
Runs well
Yes, with room to spare.

16-bit (12.3 GB) needs about 14.6 GB in use, so 9.4 GB of the 24 GB stays free: room for a larger image, a LoRA or a ControlNet.

Best file16-bit
File size12.3 GB
VRAM needed~14.6 GB
System RAM48 GB+
Memory map · RTX 3090 24 GB14.6 GB / 24 GB
012 GB24 GB
Weights 16-bit · 12.3 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 9.4 GB

01What to download

PartFileFolderSize
Modelming_image_0.1_design_bf16.safetensors
16-bit · Comfy-Org/Ming-Image
models/diffusion_models12.3 GBDownload →
Text encoderming_image_0.1_ling_mini_2.0_int8_convrot.safetensors
Ling-Mini-2.0 INT8 · Comfy-Org/Ming-Image
models/text_encoders19.5 GBDownload →
VAEming_image_vae_bf16.safetensors
Ming-Image VAE · Comfy-Org/Ming-Image
models/vae0.3 GBDownload →
Total download · keep about the same free on disk32.1 GB

Alternatives: Ling-Mini-2.0 BF16 (36.7 GB); Ling-Mini-2.0 (4-bit w4a8) (12.8 GB). Sizes from Hugging Face, 2026-10-01.

Free ComfyUI workflow, tested on my RTX 5060 Ti: INT8 workflow (.json). Drag the file into ComfyUI. All workflows →

System RAM: 48 GB or more. These files take about 32.1 GB of RAM while loaded, 38.1 GB with Windows and ComfyUI. What happens with less. calculated

02Every Ming-Image file on 24 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · Comfy-Org
12.3 GB14.6 GBfits · 9.4 GB sparethe original weightsHugging Face →
Q8_0
GGUF · realrebelai
7.3 GB9.6 GBfits · 14.4 GB sparepractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
6.2 GB8.5 GBfits · 15.5 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · realrebelai
6.8 GB9.1 GBfits · 14.9 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · realrebelai
6.2 GB8.5 GBfits · 15.5 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · realrebelai
5.9 GB8.2 GBfits · 15.8 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · realrebelai
5.1 GB7.4 GBfits · 16.6 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · realrebelai
4.7 GB7.0 GBfits · 17.0 GB spareheavy loss; a last resortHugging Face →

“Needed” adds 1.5 GB of working memory for Ming-Image and a 0.8 GB reserve. Sizes 2026-10-01. Made for 2048×2048 as well as 1024×1024; at 2048 the working memory is several times larger than the figure used here. A separate "layer" checkpoint of the same size splits a design into layers. Native in ComfyUI since v0.38.0 (late September 2026).

03Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Ming-Image on a RTX 3090 24 GB, send your time per image and peak VRAM and it will appear here, credited.

04About the RTX 3090 24 GB

The RTX 3090 24 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.

24 GB GDDR6X · 384-bit · 936 GB/s · Ampere. Everything that runs on it →

05Questions

How much VRAM does Ming-Image need?

Around 7.0 GB with the smallest file (Q2_K) and 8.5 GB with an 8-bit file (INT8). The full 16-bit file needs about 14.6 GB.

Which Ming-Image file should I download for the RTX 3090 24 GB?

16-bit (12.3 GB) from Comfy-Org/Ming-Image.

How much do I need to download for Ming-Image on the RTX 3090 24 GB?

32.1 GB: ming_image_0.1_design_bf16.safetensors, ming_image_0.1_ling_mini_2.0_int8_convrot.safetensors, ming_image_vae_bf16.safetensors.