Can the Arc B580 12 GB run Qwen-Image-Edit (2511)?
Not at full quality. The 16-bit and 8-bit files are too big for the Arc B580 12 GB; the largest that fits is Q2_K (7.5 GB).
Q2_K (7.5 GB) fits with only 1.5 GB to spare (about 10.5 GB of 12 GB). Quality: heavy loss; a last resort. For better quality, Q3_K_M (9.9 GB) also runs, with about 0.9 GB spilling into system RAM - a little slower, still practical.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | qwen-image-edit-2511-Q2_K.gguf Q2_K · unsloth/Qwen-Image-Edit-2511-GGUF | models/unet | 7.5 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 | 17.1 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 →
02Every Qwen-Image-Edit file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 40.9 GB | 43.9 GB | 31.9 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 21.8 GB | 24.8 GB | 12.8 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 20.5 GB | 23.5 GB | 11.5 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 16.9 GB | 19.9 GB | 7.9 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 15.0 GB | 18.0 GB | 6.0 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 13.2 GB | 16.2 GB | 4.2 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 9.9 GB | 12.9 GB | spills 0.9 GB | noticeable loss of detail | Hugging Face → |
| Q2_K ← GGUF · unsloth | 7.5 GB | 10.5 GB | fits · 1.5 GB spare | 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.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Qwen-Image-Edit on a Arc B580 12 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 24 GB you could run Qwen-Image-Edit at 8-bit or better (FP8, 20.5 GB) with no offloading: for example on the RTX 4090 24 GB, RTX 3090 24 GB, RX 7900 XTX 24 GB.
What changes from the Arc B580 12 GB to the RTX 5060 Ti 16 GB →
05About the Arc B580 12 GB
Intel Arc GPUs run ComfyUI through PyTorch's native XPU support on Windows 11 and Linux. Memory works the same as on NVIDIA, so the fit verdicts apply. FP8 files save memory but give no speed-up, and some custom nodes are NVIDIA-only.
12 GB GDDR6 · 192-bit · 456 GB/s · Battlemage. Everything that runs on it →
06Questions
How much VRAM does Qwen-Image-Edit need?
Around 10.5 GB with the smallest file (Q2_K) and 23.5 GB with an 8-bit file (FP8). The full 16-bit file needs about 43.9 GB.
Which Qwen-Image-Edit file should I download for the Arc B580 12 GB?
Q2_K (7.5 GB) from unsloth/Qwen-Image-Edit-2511-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Qwen-Image-Edit on the Arc B580 12 GB?
Q8_0 (21.8 GB). The Arc B580 12 GB has no FP8 maths, so FP8 (20.5 GB) only saves memory and is a step further from the original.
How much do I need to download for Qwen-Image-Edit on the Arc B580 12 GB?
17.1 GB: qwen-image-edit-2511-Q2_K.gguf, qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_vae.safetensors.