HiDream-I1 (Full) on 6 GB of VRAM
Not entirely. Even Q4_K_M is 8.3 GB over 6 GB, so ComfyUI keeps part of it in system RAM. The full, undistilled HiDream-I1: same 17B size as Dev, but with CFG and about 50 steps, so each image takes roughly twice as long.
The smallest sensible file, Q4_K_M (11.5 GB), needs about 14.3 GB - 8.3 GB more than 6 GB GPU 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.
Also try the FP8 file (17.1 GB) on NVIDIA GPUs. 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 →
01Other amounts of VRAM
02Every file, on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.2 GB | 37.0 GB | 31.0 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 18.7 GB | 21.5 GB | 15.5 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 17.1 GB | 19.9 GB | 13.9 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.7 GB | 17.5 GB | 11.5 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 13.0 GB | 15.8 GB | 9.8 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · city96 | 11.5 GB | 14.3 GB | 8.3 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 8.8 GB | 11.6 GB | 5.6 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 6.6 GB | 9.4 GB | 3.4 GB too big | heavy loss; a last resort | Hugging Face → |
“Needed” adds 2 GB of working memory for HiDream-I1 Full and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | hidream-i1-full-Q4_K_M.gguf Q4_K_M · city96/HiDream-I1-Full-gguf | models/unet | 11.5 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 | 27.7 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 27.7 GB of RAM while loaded, 33.7 GB with Windows and ComfyUI. What happens with less. calculated
04The text encoder
At 15.9 GB even the smallest CLIP-L + CLIP-G + T5-XXL + Llama 3.1 8B file is too big for 6 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: FP8 15.9 GB (all four together: CLIP-L 0.25 + CLIP-G 1.39 + T5-XXL FP8 5.16 + Llama 3.1 8B FP8 9.08 GB). Why the encoder does not count against VRAM →