Check my GPU →

Can the RTX 5070 12 GB run Ming-Image 0.1 Design?

Yes. INT8 fits on the RTX 5070 12 GB with 3.5 GB to spare.

Image model · 6.15B12 GB GDDR7 · 192-bit · 672 GB/s · BlackwellData 2026-10-01
Runs well
Yes.

Take INT8 (6.2 GB). In use it comes to about 8.5 GB, with 3.5 GB left over on 12 GB.

Best fileINT8
File size6.2 GB
VRAM needed~8.5 GB
System RAM32 GB+
Memory map · RTX 5070 12 GB8.5 GB / 12 GB
06 GB12 GB
Weights INT8 · 6.2 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 3.5 GB

01What to download

PartFileFolderSize
Modelming_image_0.1_design_int8_convrot.safetensors
INT8 · Comfy-Org/Ming-Image
models/diffusion_models6.2 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 disk25.9 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 →

02Every Ming-Image file on 12 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
12.3 GB14.6 GB2.6 GB too bigthe original weightsHugging Face →
INT8 ←
SAFETENSORS · Comfy-Org
6.2 GB8.5 GBfits · 3.5 GB sparepractically identical to the originalHugging Face →
Q8_0
GGUF · realrebelai
7.3 GB9.6 GBfits · 2.4 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · realrebelai
6.8 GB9.1 GBfits · 2.9 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · realrebelai
6.2 GB8.5 GBfits · 3.5 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · realrebelai
5.9 GB8.2 GBfits · 3.8 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · realrebelai
5.1 GB7.4 GBfits · 4.6 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · realrebelai
4.7 GB7.0 GBfits · 5.0 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 12 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 5070 12 GB, send your time per image and peak VRAM and it will appear here, credited.

05About the RTX 5070 12 GB

The RTX 5070 12 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.

12 GB GDDR7 · 192-bit · 672 GB/s · Blackwell. 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 5070 12 GB?

INT8 (6.2 GB) from Comfy-Org/Ming-Image.

How much do I need to download for Ming-Image on the RTX 5070 12 GB?

25.9 GB: ming_image_0.1_design_int8_convrot.safetensors, ming_image_0.1_ling_mini_2.0_int8_convrot.safetensors, ming_image_vae_bf16.safetensors.