Can the RTX 3070 8 GB run Wan 2.2 TI2V 5B?
Not at full quality. The 16-bit and 8-bit files are too big for the RTX 3070 8 GB; the largest that fits is Q5_K_M (3.8 GB).
Q5_K_M (3.8 GB) fits with only 0.4 GB to spare (about 7.6 GB of 8 GB). Quality: close; small differences in fine detail. For better quality, Q6_K (4.2 GB) also runs, with about 0.0 GB spilling into system RAM - a little slower, still practical.
Using Kijai's WanVideoWrapper instead of the native nodes? Its WanVideo BlockSwap node keeps part of the model in system RAM. To run the 16-bit file (10.0 GB) on RTX 3070 8 GB, start with blocks_to_swap ≈ 19 (of 30). Each block is about 0.3 GB; raise the number if you still run out of memory, lower it for speed. estimate WanVideoWrapper →
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.2-TI2V-5B-Q5_K_M.gguf Q5_K_M · QuantStack/Wan2.2-TI2V-5B-GGUF | models/unet | 3.8 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 | wan2.2_vae.safetensors Wan 2.2 VAE · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/vae | 1.4 GB | Download → |
| Total download · keep about the same free on disk | 12.0 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: text to video workflow (.json). Drag the file into ComfyUI. All workflows →
02Every Wan 2.2 5B file on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 10.0 GB | 13.8 GB | 5.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 5.4 GB | 9.2 GB | spills 1.2 GB | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 4.2 GB | 8.0 GB | spills 0.0 GB | very close to the original | Hugging Face → |
| Q5_K_M ← GGUF · QuantStack | 3.8 GB | 7.6 GB | fits · 0.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 3.4 GB | 7.2 GB | fits · 0.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 2.5 GB | 6.3 GB | fits · 1.7 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 1.9 GB | 5.7 GB | fits · 2.3 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 3 GB of working memory for Wan 2.2 5B 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 Wan 2.2 5B on a RTX 3070 8 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 10 GB you could run Wan 2.2 5B at 8-bit or better (Q8_0, 5.4 GB) with no offloading: for example on the RTX 3080 10 GB.
What changes from the RTX 3070 8 GB to the RTX 5060 Ti 16 GB → · What changes from the RTX 3070 8 GB to the RTX 3090 24 GB →
05About the RTX 3070 8 GB
The RTX 3070 8 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.
8 GB GDDR6 · 256-bit · 448 GB/s · Ampere. Everything that runs on it →
06Questions
How much VRAM does Wan 2.2 5B need?
Around 5.7 GB with the smallest file (Q2_K) and 9.2 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 13.8 GB.
Which Wan 2.2 5B file should I download for the RTX 3070 8 GB?
Q5_K_M (3.8 GB) from QuantStack/Wan2.2-TI2V-5B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
How much do I need to download for Wan 2.2 5B on the RTX 3070 8 GB?
12.0 GB: Wan2.2-TI2V-5B-Q5_K_M.gguf, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan2.2_vae.safetensors.