Can the RTX 4070 12 GB run Ming-Image 0.1 Design?
Yes. INT8 fits on the RTX 4070 12 GB with 3.5 GB to spare.
Take INT8 (6.2 GB). In use it comes to about 8.5 GB, with 3.5 GB left over on 12 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | ming_image_0.1_design_int8_convrot.safetensors INT8 · Comfy-Org/Ming-Image | models/diffusion_models | 6.2 GB | Download → |
| Text encoder | ming_image_0.1_ling_mini_2.0_int8_convrot.safetensors Ling-Mini-2.0 INT8 · Comfy-Org/Ming-Image | models/text_encoders | 19.5 GB | Download → |
| VAE | ming_image_vae_bf16.safetensors Ming-Image VAE · Comfy-Org/Ming-Image | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 25.9 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
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 12.3 GB | 14.6 GB | 2.6 GB too big | the original weights | Hugging Face → |
| INT8 ← SAFETENSORS · Comfy-Org | 6.2 GB | 8.5 GB | fits · 3.5 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · realrebelai | 7.3 GB | 9.6 GB | fits · 2.4 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · realrebelai | 6.8 GB | 9.1 GB | fits · 2.9 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 6.2 GB | 8.5 GB | fits · 3.5 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 5.9 GB | 8.2 GB | fits · 3.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 5.1 GB | 7.4 GB | fits · 4.6 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · realrebelai | 4.7 GB | 7.0 GB | fits · 5.0 GB spare | heavy loss; a last resort | Hugging 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 4070 12 GB, send your time per image and peak VRAM and it will appear here, credited.
05About the RTX 4070 12 GB
The RTX 4070 12 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.)
12 GB GDDR6X · 192-bit · 504 GB/s · Ada Lovelace. 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 4070 12 GB?
INT8 (6.2 GB) from Comfy-Org/Ming-Image.
How much do I need to download for Ming-Image on the RTX 4070 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.