HiDream-I1 (Dev) on 20 GB of VRAM
Yes, but only just: FP8 leaves 0.1 GB free on 20 GB. A 17B mixture-of-experts image model with four text encoders. The Full version has the same file sizes but uses more steps.
Runs well
Yes, just.
FP8 (17.1 GB) fits with only 0.1 GB to spare (about 19.9 GB of 20 GB).
Best fileFP8
File size17.1 GB
VRAM needed~19.9 GB
System RAM48 GB+
Memory map · 20 GB GPU19.9 GB / 20 GB
010 GB20 GB
Weights FP8 · 17.1 GBWorking memory · 2.0 GBReserve · 0.8 GBFree · 0.1 GB
calculated How this is counted.
Got an RTX 40 or 50? Swap Q8_0 for FP8 (17.1 GB): same quality class, computed natively there.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | hidream_i1_dev_fp8.safetensors FP8 · Comfy-Org/HiDream-I1_ComfyUI | models/diffusion_models | 17.1 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 | 33.3 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 33.3 GB of RAM while loaded, 39.3 GB with Windows and ComfyUI. What happens with less. calculated
02Every file, on 20 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.2 GB | 37.0 GB | 17.0 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 18.7 GB | 21.5 GB | spills 1.5 GB | practically identical to the original | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 17.1 GB | 19.9 GB | fits · 0.1 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.7 GB | 17.5 GB | fits · 2.5 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 13.0 GB | 15.8 GB | fits · 4.2 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 11.5 GB | 14.3 GB | fits · 5.7 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 8.8 GB | 11.6 GB | fits · 8.4 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 6.6 GB | 9.4 GB | fits · 10.6 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.