Check my GPU →

Can the RTX 5070 Laptop 8 GB run HiDream-O1-Image?

Not entirely. Even FP8 is 2.9 GB over 8 GB, so ComfyUI keeps part of it in system RAM.

Image model · 8.8B8 GB GDDR7 · 128-bit · 384 GB/s · Blackwell · 50–100 WData 2026-10-01
Offload
Not entirely in VRAM, but it can still run.

The smallest sensible file, FP8 (8.1 GB), needs about 10.9 GB - 2.9 GB more than RTX 5070 Laptop 8 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.

Best fileFP8
File size8.1 GB
VRAM needed~10.9 GB
System RAM16 GB+
Memory map · RTX 5070 Laptop 8 GB10.9 GB needed · 2.9 GB over 8 GB
05 GB11 GB
Weights FP8 · 8.1 GBWorking memory · 2.0 GBReserve · 0.8 GBSpills to system RAM · 2.9 GB

Also try the FP8 file (8.1 GB) on this GPU. 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 →

01With more VRAM

With 12 GB you could run HiDream-O1 at 8-bit or better (FP8, 8.1 GB) with no offloading: for example on the RTX 5070 12 GB, RTX 4070 Super 12 GB, RTX 4070 12 GB.

02Every HiDream-O1 file on 8 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
16.4 GB19.2 GB11.2 GB too bigthe original weightsHugging Face →
FP8 ←
SAFETENSORS · Comfy-Org
8.1 GB10.9 GB2.9 GB too bigpractically identical to the originalHugging 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.

03What to download

PartFileFolderSize
Checkpointhidream_o1_image_fp8_scaled.safetensors
FP8 · Comfy-Org/HiDream-O1-Image
models/checkpoints8.1 GBDownload →
Total download · keep about the same free on disk8.1 GB

One file: this model has no separate text encoder or VAE. Sizes from Hugging Face, 2026-10-01.

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 RTX 5070 Laptop 8 GB, send your time per image and peak VRAM and it will appear here, credited.

06About the RTX 5070 Laptop 8 GB

The RTX 5070 Laptop 8 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still. As a laptop GPU it runs at a lower power limit than desktop cards (50–100 W depending on the laptop). The memory verdicts are the same; speed depends heavily on how much power the laptop maker allows.

8 GB GDDR7 · 128-bit · 384 GB/s · Blackwell · 50–100 W. 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 RTX 5070 Laptop 8 GB?

FP8 (8.1 GB) from Comfy-Org/HiDream-O1-Image.

How much do I need to download for HiDream-O1 on the RTX 5070 Laptop 8 GB?

8.1 GB: hidream_o1_image_fp8_scaled.safetensors.