Can the RTX 3090 24 GB run HiDream-I1 (Dev)?
Yes, but only just: Q8_0 leaves 2.5 GB free on the RTX 3090 24 GB.
Take Q8_0 (18.7 GB). In use it comes to about 21.5 GB, with 2.5 GB left over on 24 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | hidream-i1-dev-Q8_0.gguf Q8_0 · city96/HiDream-I1-Dev-gguf | models/unet | 18.7 GB | Download → |
| Text encoder | t5xxl_fp8_e4m3fn_scaled.safetensors T5-XXL FP8 scaled · Comfy-Org/HiDream-I1_ComfyUI | models/text_encoders | 5.2 GB | Download → |
| Text encoder | clip_l_hidream.safetensors CLIP-L (HiDream) · Comfy-Org/HiDream-I1_ComfyUI | models/text_encoders | 0.2 GB | Download → |
| Text encoder | clip_g_hidream.safetensors CLIP-G (HiDream) · Comfy-Org/HiDream-I1_ComfyUI | models/text_encoders | 1.4 GB | Download → |
| Text encoder | llama_3.1_8b_instruct_fp8_scaled.safetensors Llama 3.1 8B Instruct FP8 · Comfy-Org/HiDream-I1_ComfyUI | models/text_encoders | 9.1 GB | Download → |
| VAE | ae.safetensors FLUX.1 VAE (ae) · Comfy-Org/HiDream-I1_ComfyUI | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 34.9 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 34.9 GB of RAM while loaded, 40.9 GB with Windows and ComfyUI. What happens with less. calculated
02Every HiDream-I1 file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.2 GB | 37.0 GB | 13.0 GB too big | the original weights | Hugging Face → |
| Q8_0 ← GGUF · city96 | 18.7 GB | 21.5 GB | fits · 2.5 GB spare | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 17.1 GB | 19.9 GB | fits · 4.1 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.7 GB | 17.5 GB | fits · 6.5 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 13.0 GB | 15.8 GB | fits · 8.2 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 11.5 GB | 14.3 GB | fits · 9.7 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 8.8 GB | 11.6 GB | fits · 12.4 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 6.6 GB | 9.4 GB | fits · 14.6 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 2 GB of working memory for HiDream-I1 and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
| Label | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|
| reported | HiDream Full fp8 (T5 fp8, Llama3.1 fp8 scaled) “ComfyUI Full example from their page at https://comfyanonymous.github.io/ComfyUI_examples/hidream/ runs at 115.09s on my RTX 3090, from cold start.” HiDream-I1 Full via ComfyUI example workflow, Windows portable; cold start incl. load; resolution/steps not restated | 115.09 s / image | — | 2025-04-18 | huggingface.co → |
Other people's numbers are copied as published, with a link. Send yours.
04About the RTX 3090 24 GB
The RTX 3090 24 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.
24 GB GDDR6X · 384-bit · 936 GB/s · Ampere. Everything that runs on it →
05Questions
How much VRAM does HiDream-I1 need?
Around 9.4 GB with the smallest file (Q2_K) and 19.9 GB with an 8-bit file (FP8). The full 16-bit file needs about 37.0 GB.
Which HiDream-I1 file should I download for the RTX 3090 24 GB?
Q8_0 (18.7 GB) from city96/HiDream-I1-Dev-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for HiDream-I1 on the RTX 3090 24 GB?
Q8_0 (18.7 GB). The RTX 3090 24 GB has no FP8 maths, so FP8 (17.1 GB) only saves memory and is a step further from the original.
How much do I need to download for HiDream-I1 on the RTX 3090 24 GB?
34.9 GB: hidream-i1-dev-Q8_0.gguf, t5xxl_fp8_e4m3fn_scaled.safetensors, clip_l_hidream.safetensors, clip_g_hidream.safetensors, llama_3.1_8b_instruct_fp8_scaled.safetensors, ae.safetensors.