Can the Mac 16 GB run Ming-Image 0.1 Design?
Download Q8_0 (7.3 GB). With the model's working memory it needs about 9.6 GB, leaving 3.1 GB spare on 12.7 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_w4a8.safetensors Ling-Mini-2.0 (4-bit w4a8) · Comfy-Org/Ming-Image | models/text_encoders | 12.8 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 | 20.4 GB | |||
Alternatives: Ling-Mini-2.0 BF16 (36.7 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. On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. 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 →
Shared memory: about 26.4 GB of your 16 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 10.4 GB more than there is. It still runs: while the model works, the system compresses or swaps the idle text encoder, so loading and changing the prompt get slower. A smaller file or text encoder avoids that. calculated
02Every Ming-Image file on 12.7 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 12.3 GB | 14.6 GB | spills 1.9 GB | the original weights | Hugging Face → |
| Q8_0 ← GGUF · realrebelai | 7.3 GB | 9.6 GB | fits · 3.1 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · realrebelai | 6.8 GB | 9.1 GB | fits · 3.6 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 6.2 GB | 8.5 GB | fits · 4.2 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 5.9 GB | 8.2 GB | fits · 4.5 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 5.1 GB | 7.4 GB | fits · 5.3 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · realrebelai | 4.7 GB | 7.0 GB | fits · 5.7 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). FP8 and INT8 files are left out on a Mac: Apple GPUs cannot compute FP8, so ComfyUI either fails to load them or converts them back to 16-bit, which saves no memory. Use a 16-bit or GGUF file.
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 12.7 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.
04About this GPU
A Mac with 16 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 12.7 GB of it by default (older macOS versions: about 11.5 GB); that is the figure used here. ComfyUI can go past it, but macOS then starts compressing and swapping memory and everything slows down. ComfyUI runs on Apple GPUs through PyTorch's MPS backend. 16-bit and GGUF files work; FP8 and INT8 files do not save memory on a Mac, so they are skipped. Speed is the catch: even the fastest Macs are several times slower per image than a desktop RTX card. Chips sold with 16 GB: M1, M1 Pro, M2, M2 Pro, M3, M4, M5, M6 (memory bandwidth 68.25–200 GB/s — the higher, the faster). Everything about Macs and local AI →
Mac 16 GB: 16 GB unified · ~12.7 GB for the GPU · 68.25–200 GB/s · Apple Silicon. Everything that runs on the Mac 16 GB →
05What more VRAM would change
Nothing to gain for this model: the Mac 16 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Ming-Image on a Mac 16 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
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), counting working memory and a small system reserve. The full 16-bit file needs about 14.6 GB.
Which Ming-Image file should I download for the Mac 16 GB?
Q8_0 (7.3 GB) from realrebelai/Ming-Image_GGUFs. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
Is FP8 faster than GGUF on the Mac 16 GB?
No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.
How much do I need to download for Ming-Image on the Mac 16 GB?
About 20.4 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 12.7 GB card, 32 GB of system RAM or more is recommended.