Can the Mac 64 GB run Stable Diffusion 1.5?
Download 16-bit (2.1 GB). With the model's working memory it needs about 3.3 GB, leaving 52.4 GB spare on 55.7 GB. Quality: the original weights.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Checkpoint | v1-5-pruned-emaonly-fp16.safetensors 16-bit · Comfy-Org/stable-diffusion-v1-5-archive | models/checkpoints | 2.1 GB | Download → |
| Total download · keep about the same free on disk | 2.1 GB | |||
One file: the checkpoint already contains the text encoders and the VAE. On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
Shared memory: about 8.1 GB of your 64 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That leaves room, so nothing has to be swapped to disk. calculated
02Every SD 1.5 file on 55.7 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 2.1 GB | 3.3 GB | fits · 52.4 GB spare | the original weights | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 0.8 GB working memory for this model + 0.8 GB kept free for the system. The 2.13 GB checkpoint also holds the text encoder and VAE; the UNet alone is about 1.7 GB at 16-bit.
03The text encoder
The text encoder is inside the checkpoint, so there is nothing extra to download.
04About this GPU
A Mac with 64 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 55.7 GB of it by default (older macOS versions: about 51.5 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 64 GB: M1 Max, M1 Ultra, M2 Max, M2 Ultra, M3 Max, M4 Pro, M4 Max, M5 Pro, M5 Max (memory bandwidth 273–800 GB/s — the higher, the faster). Everything about Macs and local AI →
Mac 64 GB: 64 GB unified · ~55.7 GB for the GPU · 273–800 GB/s · Apple Silicon. Everything that runs on the Mac 64 GB →
05What more VRAM would change
Nothing to gain for this model: the Mac 64 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 SD 1.5 on a Mac 64 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does SD 1.5 need?
Around 3.3 GB with the smallest file (16-bit), counting working memory and a small system reserve.
Which SD 1.5 file should I download for the Mac 64 GB?
16-bit (2.1 GB) from Comfy-Org/stable-diffusion-v1-5-archive.
Is FP8 faster than GGUF on the Mac 64 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 SD 1.5 on the Mac 64 GB?
About 2.1 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 55.7 GB card, 16 GB of system RAM or more is recommended.