Can the Mac 16 GB run HiDream-O1-Image?
Not entirely. Even 16-bit is 6.5 GB over 12.7 GB, so ComfyUI keeps part of it in system RAM.
The smallest sensible file, 16-bit (16.4 GB), needs about 19.2 GB - 6.5 GB more than Mac 16 GB has. ComfyUI can still run it by streaming part of the model from system RAM. How much slower that is depends on your ComfyUI version, the file format and the PCIe link - see the note below.
01With more VRAM
With 20 GB you could run HiDream-O1 at 8-bit or better (16-bit, 16.4 GB) with no offloading.
02Every HiDream-O1 file on 12.7 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 16.4 GB | 19.2 GB | 6.5 GB too big | the original weights | Hugging Face → |
“Needed” adds 2 GB of working memory for HiDream-O1 and a 0.8 GB reserve. Sizes 2026-10-01. The Comfy-Org files are complete checkpoints (loaded from the checkpoints folder); there is no separate text encoder or VAE to add. No GGUF version was found. 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.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Checkpoint | hidream_o1_image_bf16.safetensors 16-bit · Comfy-Org/HiDream-O1-Image | models/checkpoints | 16.4 GB | Download → |
| Total download · keep about the same free on disk | 16.4 GB | |||
One file: this model has no separate text encoder or VAE. On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. Sizes from Hugging Face, 2026-10-01.
Shared memory: about 22.4 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 6.4 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
04The text encoder
This model has no separate text encoder: reading the prompt is built into the model itself, so its memory is already in the file sizes above.
05Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run HiDream-O1 on a Mac 16 GB, send your time per image and peak VRAM and it will appear here, credited.
06About the Mac 16 GB
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 →
16 GB unified · ~12.7 GB for the GPU · 68.25–200 GB/s · Apple Silicon. Everything that runs on it →
07Questions
How much VRAM does HiDream-O1 need?
Around 10.9 GB with the smallest file (FP8) and 10.9 GB with an 8-bit file (FP8). The full 16-bit file needs about 19.2 GB.
Which HiDream-O1 file should I download for the Mac 16 GB?
16-bit (16.4 GB) from Comfy-Org/HiDream-O1-Image.
How much do I need to download for HiDream-O1 on the Mac 16 GB?
16.4 GB: hidream_o1_image_bf16.safetensors.