Check my GPU →

Ming-Image 0.1 Design on 6 GB of VRAM

Not entirely. Even Q3_K_M is 1.4 GB over 6 GB, so ComfyUI keeps part of it in system RAM. inclusionAI's 6B model from September 2026 for design work: posters, UI mock-ups and text-heavy layouts, with transparent (RGBA) output. The image model is small, but its text encoder is a big language model (12.8–36.7 GB), so system RAM matters as much as VRAM.

Image model · 6.15BAny 6 GB GPUData 2026-10-01
Offload
Not entirely in VRAM, but it can still run.

Nothing fits entirely, but Q3_K_M (5.1 GB) overflows by only about 1.4 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.

Best fileQ3_K_M
File size5.1 GB
VRAM needed~7.4 GB
System RAM32 GB+
Memory map · 6 GB GPU7.4 GB needed · 1.4 GB over 6 GB
04 GB7 GB
Weights Q3_K_M · 5.1 GBWorking memory · 1.5 GBReserve · 0.8 GBSpills to system RAM · 1.4 GB

Also try the INT8 file (6.2 GB) on NVIDIA GPUs. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. Dynamic VRAM →

02Every file, on 6 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
12.3 GB14.6 GB8.6 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · realrebelai
7.3 GB9.6 GB3.6 GB too bigpractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
6.2 GB8.5 GB2.5 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · realrebelai
6.8 GB9.1 GB3.1 GB too bigvery close to the originalHugging Face →
Q5_K_M
GGUF · realrebelai
6.2 GB8.5 GB2.5 GB too bigclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · realrebelai
5.9 GB8.2 GB2.2 GB too biggood; some loss in fine detail and textHugging Face →
Q3_K_M ←
GGUF · realrebelai
5.1 GB7.4 GBspills 1.4 GBnoticeable loss of detailHugging Face →
Q2_K
GGUF · realrebelai
4.7 GB7.0 GBspills 1.0 GBheavy 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).

03What to download

PartFileFolderSize
ModelMing-Image-0.1-Design-Q3_K_M.gguf
Q3_K_M · realrebelai/Ming-Image_GGUFs
models/unet5.1 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 disk24.9 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 →

04The text encoder

At 12.8 GB even the smallest Ling-Mini-2.0 (a large language model) file is too big for 6 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 →