| File | qwen_image_fp8_e4m3fn.safetensors |
| Model | Qwen-Image (image model, 20B) |
| Precision | FP8 |
| Size | 20.4 GB |
| VRAM to fit | about 23.2 GB |
| Folder | ComfyUI/models/diffusion_models/ |
| Loader node | Load Diffusion Model (UNETLoader) |
| Source | Comfy-Org/Qwen-Image_ComfyUI on Hugging Face |
Download qwen_image_fp8_e4m3fn.safetensors (20.4 GB)
Where to put it
Put the file in ComfyUI/models/diffusion_models/ (portable version: ComfyUI_windows_portable/ComfyUI/models/diffusion_models/). Older guides say models/unet: that folder still works. Press R in ComfyUI or restart it, then pick the file in Load Diffusion Model (UNETLoader). Not for Mac: FP8 and INT8 files do not load on Apple Silicon.
If a workflow says “Value not in list” for that node, the workflow expects a file with another name. Click the node and choose this one.
Which graphics cards it fits
| VRAM | This file | Best file for that card (RTX 40/50) | |
|---|---|---|---|
| 6 GB | Not practical | Short by 17.2 GB | qwen-image-Q2_K.gguf (7.1 GB) |
| 8 GB | Not practical | Short by 15.2 GB | qwen-image-Q2_K.gguf (7.1 GB) |
| 10 GB | Not practical | Short by 13.2 GB | qwen-image-Q2_K.gguf (7.1 GB) |
| 12 GB | Offload only | Short by 11.2 GB: runs with part of it in system RAM, slower | qwen-image-Q2_K.gguf (7.1 GB) |
| 16 GB | Offload only | Short by 7.2 GB: runs with part of it in system RAM, slower | qwen-image-Q4_K_M.gguf (13.1 GB) |
| 20 GB | Offload only | Short by 3.2 GB: runs with part of it in system RAM, slower | qwen-image-Q6_K.gguf (16.8 GB) |
| 24 GB | Runs well | Fits in VRAM, 0.8 GB to spare | this file |
| 32 GB | Runs well | Fits in VRAM, 8.8 GB to spare | this file |
| 48 GB | Runs well | Fits in VRAM, 24.8 GB to spare | qwen_image_bf16.safetensors (40.9 GB) |
Need = file × 1 + 2 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site. FP8 files do not load on a Mac (Apple Silicon); use a 16-bit or GGUF file there.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | qwen_image_fp8_e4m3fn.safetensors | 20.4 GB | models/diffusion_models |
| Text encoder | qwen_2.5_vl_7b_fp8_scaled.safetensors | 9.4 GB | models/text_encoders |
| VAE | qwen_image_vae.safetensors | 0.3 GB | models/vae |
30.1 GB in total. Smaller text-encoder versions and other options are on the Qwen-Image page.
Other files of Qwen-Image
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| qwen_image_bf16.safetensors | 16-bit | 40.9 GB | 43.7 GB |
| qwen-image-Q8_0.gguf | Q8_0 | 21.8 GB | 24.6 GB |
| qwen_image_fp8_e4m3fn.safetensors | FP8 | 20.4 GB | 23.2 GB |
| qwen-image-Q6_K.gguf | Q6_K | 16.8 GB | 19.6 GB |
| qwen-image-Q5_K_M.gguf | Q5_K_M | 14.9 GB | 17.7 GB |
| qwen-image-Q4_K_M.gguf | Q4_K_M | 13.1 GB | 15.9 GB |
| qwen-image-Q3_K_M.gguf | Q3_K_M | 9.7 GB | 12.5 GB |
| qwen-image-Q2_K.gguf | Q2_K | 7.1 GB | 9.9 GB |
Same model, different compression. 8-bit files (FP8, INT8, Q8_0) look almost the same as 16-bit; below Q5 the loss starts to show.
Want the answer for your exact card? Check your GPU. Every file of every model: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).