| File | qwen_image_2.1_Q8_0.gguf |
| Model | Qwen-Image 2.1 (image model, 7.1B) |
| Precision | Q8_0 |
| Size | 7.6 GB |
| VRAM to fit | about 9.9 GB |
| Folder | ComfyUI/models/unet/ |
| Loader node | Unet Loader (GGUF) from the ComfyUI-GGUF custom nodes |
| Source | Abiray/Qwen-Image-2.1-GGUF on Hugging Face |
Download qwen_image_2.1_Q8_0.gguf (7.6 GB)
Where to put it
Put the file in ComfyUI/models/unet/ (portable version: ComfyUI_windows_portable/ComfyUI/models/unet/). Press R in ComfyUI or restart it, then pick the file in Unet Loader (GGUF) from the ComfyUI-GGUF custom nodes.
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 | Offload only | Short by 3.9 GB: runs with part of it in system RAM, slower | qwen_image_2.1_Q3_K_M.gguf (3.2 GB) |
| 8 GB | Offload only | Short by 1.9 GB: runs with part of it in system RAM, slower | qwen_image_2.1_Q5_K_M.gguf (5.0 GB) |
| 10 GB | Runs well | Fits in VRAM, 0.1 GB to spare | qwen_image_2.1_int8_convrot.safetensors (7.3 GB) |
| 12 GB | Runs well | Fits in VRAM, 2.1 GB to spare | qwen_image_2.1_int8_convrot.safetensors (7.3 GB) |
| 16 GB | Runs well | Fits in VRAM, 6.1 GB to spare | qwen_image_2.1_int8_convrot.safetensors (7.3 GB) |
| 20 GB | Runs well | Fits in VRAM, 10.1 GB to spare | qwen_image_2.1_bf16.safetensors (14.2 GB) |
| 24 GB | Runs well | Fits in VRAM, 14.1 GB to spare | qwen_image_2.1_bf16.safetensors (14.2 GB) |
| 32 GB | Runs well | Fits in VRAM, 22.1 GB to spare | qwen_image_2.1_bf16.safetensors (14.2 GB) |
| 48 GB | Runs well | Fits in VRAM, 38.1 GB to spare | qwen_image_2.1_bf16.safetensors (14.2 GB) |
Need = file × 1 + 1.5 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site.
Measured with this exact file
| GPU | Time | Size | Steps | Peak VRAM | Source |
|---|---|---|---|---|---|
| RTX 5060 Ti 16 GB | 43.6 s per image | 1024x1024 | 25 | 14.8 GB | measured by me, 2026-10-04 |
Time = sampling + VAE decode, after a warm-up run. Peak VRAM = memory in use on the whole card. How I measure.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | qwen_image_2.1_Q8_0.gguf | 7.6 GB | models/unet |
| Text encoder | qwen3vl_8b_int8_convrot.safetensors | 9.4 GB | models/text_encoders |
| VAE | qwen_image_2.1_vae_bf16.safetensors | 0.7 GB | models/vae |
17.6 GB in total. Smaller text-encoder versions and other options are on the Qwen-Image 2.1 page.
Other files of Qwen-Image 2.1
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| qwen_image_2.1_bf16.safetensors | 16-bit | 14.2 GB | 16.5 GB |
| qwen_image_2.1_Q8_0.gguf | Q8_0 | 7.6 GB | 9.9 GB |
| qwen_image_2.1_int8_convrot.safetensors | INT8 | 7.3 GB | 9.6 GB |
| qwen_image_2.1_Q6_K.gguf | Q6_K | 5.9 GB | 8.2 GB |
| qwen_image_2.1_Q5_K_M.gguf | Q5_K_M | 5.0 GB | 7.3 GB |
| qwen_image_2.1_Q4_K_M.gguf | Q4_K_M | 4.2 GB | 6.5 GB |
| qwen_image_2.1_Q3_K_M.gguf | Q3_K_M | 3.2 GB | 5.5 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).