HiDream-O1-Image on 16 GB of VRAM
Yes. FP8 fits on 16 GB with 5.1 GB to spare. A 2026 all-in-one 8.8B model built on Qwen3-VL: no separate text encoder and no VAE. It generates, edits and personalises up to 2048×2048.
Take FP8 (8.1 GB). In use it comes to about 10.9 GB, with 5.1 GB left over on 16 GB.
Got an RTX 40 or 50? Swap Q8_0 for FP8 (8.1 GB): same quality class, computed natively there.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Checkpoint | hidream_o1_image_fp8_scaled.safetensors FP8 · Comfy-Org/HiDream-O1-Image | models/checkpoints | 8.1 GB | Download → |
| Total download · keep about the same free on disk | 8.1 GB | |||
One file: this model has no separate text encoder or VAE. Sizes from Hugging Face, 2026-10-01.
02Every file, on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 16.4 GB | 19.2 GB | 3.2 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 8.1 GB | 10.9 GB | fits · 5.1 GB spare | practically identical to the original | 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.
03The 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.