Check my GPU →

Can the RTX 3080 10 GB run Ming-Image 0.1 Design?

Yes, but only just: Q8_0 leaves 0.4 GB free on the RTX 3080 10 GB.

Image model · 6.15B10 GB GDDR6X · 320-bit · 760 GB/s · AmpereData 2026-10-01
Runs well
Yes, just.

Q8_0 (7.3 GB) fits with only 0.4 GB to spare (about 9.6 GB of 10 GB).

Best fileQ8_0
File size7.3 GB
VRAM needed~9.6 GB
System RAM48 GB+
Memory map · RTX 3080 10 GB9.6 GB / 10 GB
05 GB10 GB
Weights Q8_0 · 7.3 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 0.4 GB

01What to download

PartFileFolderSize
ModelMing-Image-0.1-Design-Q8_0.gguf
Q8_0 · realrebelai/Ming-Image_GGUFs
models/unet7.3 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 disk27.1 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 27.1 GB of RAM while loaded, 33.1 GB with Windows and ComfyUI. What happens with less. calculated

02Every Ming-Image file on 10 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
12.3 GB14.6 GB4.6 GB too bigthe original weightsHugging Face →
Q8_0 ←
GGUF · realrebelai
7.3 GB9.6 GBfits · 0.4 GB sparepractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
6.2 GB8.5 GBfits · 1.5 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · realrebelai
6.8 GB9.1 GBfits · 0.9 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · realrebelai
6.2 GB8.5 GBfits · 1.5 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · realrebelai
5.9 GB8.2 GBfits · 1.8 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · realrebelai
5.1 GB7.4 GBfits · 2.6 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · realrebelai
4.7 GB7.0 GBfits · 3.0 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).

03The text encoder

At 12.8 GB even the smallest Ling-Mini-2.0 (a large language model) file is too big for 10 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 36.7 GB, INT8 19.5 GB, 4-bit w4a8 12.8 GB (GGUF versions from realrebelai: Q4_K_M 11.5 GB, Q2_K 7.9 GB). Why the encoder does not count against VRAM →

04Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Ming-Image on a RTX 3080 10 GB, send your time per image and peak VRAM and it will appear here, credited.

05About the RTX 3080 10 GB

The RTX 3080 10 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.

10 GB GDDR6X · 320-bit · 760 GB/s · Ampere. Everything that runs on it →

06Questions

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 3080 10 GB?

Q8_0 (7.3 GB) from realrebelai/Ming-Image_GGUFs. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.

How much do I need to download for Ming-Image on the RTX 3080 10 GB?

27.1 GB: Ming-Image-0.1-Design-Q8_0.gguf, ming_image_0.1_ling_mini_2.0_int8_convrot.safetensors, ming_image_vae_bf16.safetensors.