Qwen-Image-Edit (2511) on 8 GB of VRAM
Not entirely. Even Q4_K_M is 8.2 GB over 8 GB, so ComfyUI keeps part of it in system RAM. The editing version of Qwen-Image, release 2511. Same 20B size and the same text encoder as Qwen-Image.
The smallest sensible file, Q4_K_M (13.2 GB), needs about 16.2 GB - 8.2 GB more than 8 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 (20.5 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 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.9 GB | 43.9 GB | 35.9 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 21.8 GB | 24.8 GB | 16.8 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 20.5 GB | 23.5 GB | 15.5 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 16.9 GB | 19.9 GB | 11.9 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 15.0 GB | 18.0 GB | 10.0 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · unsloth | 13.2 GB | 16.2 GB | 8.2 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 9.9 GB | 12.9 GB | 4.9 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 7.5 GB | 10.5 GB | 2.5 GB too big | heavy loss; a last resort | Hugging Face → |
“Needed” adds 2.2 GB of working memory for Qwen-Image-Edit and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | qwen-image-edit-2511-Q4_K_M.gguf Q4_K_M · unsloth/Qwen-Image-Edit-2511-GGUF | models/unet | 13.2 GB | Download → |
| Text encoder | qwen_2.5_vl_7b_fp8_scaled.safetensors Qwen2.5-VL 7B FP8 · Comfy-Org/Qwen-Image_ComfyUI | models/text_encoders | 9.4 GB | Download → |
| VAE | qwen_image_vae.safetensors Qwen-Image VAE · Comfy-Org/Qwen-Image_ComfyUI | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 22.9 GB | |||
Alternatives: Qwen2.5-VL 7B BF16 (16.6 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: GGUF Q4_K_M + 4-step LoRA workflow (.json). Drag the file into ComfyUI. All workflows →
04The text encoder
At 9.4 GB even the smallest Qwen2.5-VL 7B file is too big for 8 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 16.6 GB, FP8 9.4 GB. Why the encoder does not count against VRAM →