| File | qwen_image_edit_2511_bf16.safetensors |
| Model | Qwen-Image-Edit (2511) (image model, 20B) |
| Precision | 16-bit |
| Size | 40.9 GB |
| VRAM to fit | about 43.9 GB |
| Folder | ComfyUI/models/diffusion_models/ |
| Loader node | Load Diffusion Model (UNETLoader) |
| Source | Comfy-Org/Qwen-Image-Edit_ComfyUI on Hugging Face |
Download qwen_image_edit_2511_bf16.safetensors (40.9 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).
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 37.9 GB | qwen-image-edit-2511-Q2_K.gguf (7.5 GB) |
| 8 GB | Not practical | Short by 35.9 GB | qwen-image-edit-2511-Q4_K_M.gguf (13.2 GB) |
| 10 GB | Not practical | Short by 33.9 GB | qwen-image-edit-2511-Q2_K.gguf (7.5 GB) |
| 12 GB | Not practical | Short by 31.9 GB | qwen-image-edit-2511-Q2_K.gguf (7.5 GB) |
| 16 GB | Not practical | Short by 27.9 GB | qwen-image-edit-2511-Q3_K_M.gguf (9.9 GB) |
| 20 GB | Not practical | Short by 23.9 GB | qwen-image-edit-2511-Q6_K.gguf (16.9 GB) |
| 24 GB | Offload only | Short by 19.9 GB: runs with part of it in system RAM, slower | qwen_image_edit_2511_fp8mixed.safetensors (20.5 GB) |
| 32 GB | Offload only | Short by 11.9 GB: runs with part of it in system RAM, slower | qwen_image_edit_2511_fp8mixed.safetensors (20.5 GB) |
| 48 GB | Runs well | Fits in VRAM, 4.1 GB to spare | this file |
Need = file × 1 + 2.2 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | qwen_image_edit_2511_bf16.safetensors | 40.9 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 |
50.5 GB in total. Smaller text-encoder versions and other options are on the Qwen-Image-Edit page.
Other files of Qwen-Image-Edit
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| qwen_image_edit_2511_bf16.safetensors | 16-bit | 40.9 GB | 43.9 GB |
| qwen-image-edit-2511-Q8_0.gguf | Q8_0 | 21.8 GB | 24.8 GB |
| qwen_image_edit_2511_fp8mixed.safetensors | FP8 | 20.5 GB | 23.5 GB |
| qwen-image-edit-2511-Q6_K.gguf | Q6_K | 16.9 GB | 19.9 GB |
| qwen-image-edit-2511-Q5_K_M.gguf | Q5_K_M | 15.0 GB | 18.0 GB |
| qwen-image-edit-2511-Q4_K_M.gguf | Q4_K_M | 13.2 GB | 16.2 GB |
| qwen-image-edit-2511-Q3_K_M.gguf | Q3_K_M | 9.9 GB | 12.9 GB |
| qwen-image-edit-2511-Q2_K.gguf | Q2_K | 7.5 GB | 10.5 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).