Ming-Image 0.1 Design on 10 GB of VRAM
Download Q8_0 (7.3 GB). With the model's working memory it needs about 9.6 GB, leaving 0.4 GB spare on 10 GB. Quality: practically identical to the original.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Ming-Image-0.1-Design-Q8_0.gguf Q8_0 · realrebelai/Ming-Image_GGUFs | models/unet | 7.3 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 | 27.1 GB | |||
Alternatives: Ling-Mini-2.0 BF16 (36.7 GB); Ling-Mini-2.0 (4-bit w4a8) (12.8 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 (2026-10-01). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
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. 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 27.1 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 33.1 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every file, on 10 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 12.3 GB | 14.6 GB | 4.6 GB too big | the original weights | Hugging Face → |
| Q8_0 ← GGUF · realrebelai | 7.3 GB | 9.6 GB | fits · 0.4 GB spare | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 6.2 GB | 8.5 GB | fits · 1.5 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · realrebelai | 6.8 GB | 9.1 GB | fits · 0.9 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 6.2 GB | 8.5 GB | fits · 1.5 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 5.9 GB | 8.2 GB | fits · 1.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 5.1 GB | 7.4 GB | fits · 2.6 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · realrebelai | 4.7 GB | 7.0 GB | fits · 3.0 GB spare | heavy loss; a last resort | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-10-01. “Needed” = file + 1.5 GB working memory for this model + 0.8 GB kept free for the system. 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
Ling-Mini-2.0 (a large language model): 36.7 GB as 16-bit, 19.5 GB as INT8, 12.8 GB as 4-bit w4a8 (GGUF versions from realrebelai: Q4_K_M 11.5 GB, Q2_K 7.9 GB). 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 10 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.