Can the RTX 4070 Super 12 GB run Wan 2.2 S2V 14B?
Not entirely. Even Q4_K_M is 6.7 GB over 12 GB, so ComfyUI keeps part of it in system RAM.
The smallest sensible file, Q4_K_M (13.9 GB), needs about 18.7 GB - 6.7 GB more than RTX 4070 Super 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.
Also try the FP8 file (16.4 GB) on this GPU. 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 →
01With more VRAM
With 24 GB you could run Wan 2.2 S2V 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 RTX 4070 Super 12 GB to the RTX 5070 Ti 16 GB → · What changes from the RTX 4070 Super 12 GB to the RTX 3090 24 GB →
02Every Wan 2.2 S2V file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 32.6 GB | 37.4 GB | 25.4 GB too big | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 16.4 GB | 21.2 GB | 9.2 GB too big | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · QuantStack | 19.6 GB | 24.4 GB | 12.4 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 16.2 GB | 21.0 GB | 9.0 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 15.0 GB | 19.8 GB | 7.8 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · QuantStack | 13.9 GB | 18.7 GB | 6.7 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 11.4 GB | 16.2 GB | 4.2 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 9.5 GB | 14.3 GB | 2.3 GB too big | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4 GB of working memory for Wan 2.2 S2V and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.2-S2V-14B-Q4_K_M.gguf Q4_K_M · QuantStack/Wan2.2-S2V-14B-GGUF | models/unet | 13.9 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_2.2_ComfyUI_Repackaged | models/vae | 0.3 GB | Download → |
| Also needed | wav2vec2_large_english_fp16.safetensors wav2vec2 large English FP16 (audio encoder) · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/audio_encoders | 0.6 GB | Download → |
| Total download · keep about the same free on disk | 21.5 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 2.2 S2V on a RTX 4070 Super 12 GB, send your time per image and peak VRAM and it will appear here, credited.
05About the RTX 4070 Super 12 GB
The RTX 4070 Super 12 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)
12 GB GDDR6X · 192-bit · 504 GB/s · Ada Lovelace. Everything that runs on it →
06Questions
How much VRAM does Wan 2.2 S2V need?
Around 14.3 GB with the smallest file (Q2_K) and 21.2 GB with an 8-bit file (FP8). The full 16-bit file needs about 37.4 GB.
Which Wan 2.2 S2V file should I download for the RTX 4070 Super 12 GB?
Q4_K_M (13.9 GB) from QuantStack/Wan2.2-S2V-14B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Wan 2.2 S2V on the RTX 4070 Super 12 GB?
FP8 (16.4 GB): the RTX 4070 Super 12 GB computes it natively, while Q8_0 (19.6 GB) is unpacked on the fly.
How much do I need to download for Wan 2.2 S2V on the RTX 4070 Super 12 GB?
21.5 GB: Wan2.2-S2V-14B-Q4_K_M.gguf, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wav2vec2_large_english_fp16.safetensors.