Can the Arc B580 12 GB run Wan 2.1 I2V 14B 720P?
Not entirely. Even Q4_K_M is 6.1 GB over 12 GB, so ComfyUI keeps part of it in system RAM.
The smallest sensible file, Q4_K_M (11.3 GB), needs about 18.1 GB - 6.1 GB more than Arc B580 12 GB 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.
Using Kijai's WanVideoWrapper instead of the native nodes? Its WanVideo BlockSwap node keeps part of the model in system RAM. To run the FP8 file (16.4 GB) on Arc B580 12 GB, start with blocks_to_swap ≈ 29 (of 40). Each block is about 0.4 GB; raise the number if you still run out of memory, lower it for speed. estimate WanVideoWrapper →
01With more VRAM
With 24 GB you could run Wan 2.1 I2V 720P at 8-bit or better (FP8, 16.4 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 →
02Every Wan 2.1 I2V 720P file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 32.8 GB | 39.6 GB | 27.6 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 18.1 GB | 24.9 GB | 12.9 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 16.4 GB | 23.2 GB | 11.2 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.2 GB | 21.0 GB | 9.0 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 12.7 GB | 19.5 GB | 7.5 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · city96 | 11.3 GB | 18.1 GB | 6.1 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 8.6 GB | 15.4 GB | 3.4 GB too big | noticeable loss of detail | Hugging Face → |
“Needed” adds 6 GB of working memory for Wan 2.1 I2V 720P and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.1-i2v-14b-720p-Q4_K_M.gguf Q4_K_M · city96/Wan2.1-I2V-14B-720P-gguf | models/unet | 11.3 GB | Download → |
| Text encoder | umt5_xxl_fp8_e4m3fn_scaled.safetensors UMT5-XXL FP8 (scaled) · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/text_encoders | 6.7 GB | Download → |
| VAE | wan_2.1_vae.safetensors Wan 2.1 VAE · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/vae | 0.3 GB | Download → |
| Also needed | clip_vision_h.safetensors CLIP Vision H · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/clip_vision | 1.3 GB | Download → |
| Total download · keep about the same free on disk | 19.6 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
04Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.1 I2V 720P on a Arc B580 12 GB, send your time per image and peak VRAM and it will appear here, credited.
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 Wan 2.1 I2V 720P need?
Around 15.4 GB with the smallest file (Q3_K_M) and 23.2 GB with an 8-bit file (FP8). The full 16-bit file needs about 39.6 GB.
Which Wan 2.1 I2V 720P file should I download for the Arc B580 12 GB?
Q4_K_M (11.3 GB) from city96/Wan2.1-I2V-14B-720P-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Wan 2.1 I2V 720P on the Arc B580 12 GB?
Q8_0 (18.1 GB). The Arc B580 12 GB has no FP8 maths, so FP8 (16.4 GB) only saves memory and is a step further from the original.
How much do I need to download for Wan 2.1 I2V 720P on the Arc B580 12 GB?
19.6 GB: wan2.1-i2v-14b-720p-Q4_K_M.gguf, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, clip_vision_h.safetensors.