Can the RTX 4070 12 GB run Wan 2.2 TI2V 5B?
Download Q8_0 (5.4 GB). With the model's working memory it needs about 9.2 GB, leaving 2.8 GB spare on 12 GB. Quality: practically identical to the original.
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 4070 12 GB, start with blocks_to_swap ≈ 7 (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-Q8_0.gguf Q8_0 · QuantStack/Wan2.2-TI2V-5B-GGUF | models/unet | 5.4 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 | 13.5 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 13.5 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 19.5 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every Wan 2.2 5B file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 10.0 GB | 13.8 GB | spills 1.8 GB | the original weights | Hugging Face → |
| Q8_0 ← GGUF · QuantStack | 5.4 GB | 9.2 GB | fits · 2.8 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 4.2 GB | 8.0 GB | fits · 4.0 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 3.8 GB | 7.6 GB | fits · 4.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 3.4 GB | 7.2 GB | fits · 4.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 2.5 GB | 6.3 GB | fits · 5.7 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 1.9 GB | 5.7 GB | fits · 6.3 GB spare | heavy loss; a last resort | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 3 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
UMT5-XXL: 11.4 GB as 16-bit, 6.7 GB as FP8, 3.7 GB as GGUF Q4_K_M. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 12 GB the FP8 encoder fits on its own, so prompt encoding stays fast.
04About this GPU
The RTX 4070 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.)
RTX 4070 12 GB: 12 GB GDDR6X · 192-bit · 504 GB/s · Ada Lovelace. Everything that runs on the RTX 4070 12 GB →
05What more VRAM would change
Nothing to gain for this model: the RTX 4070 12 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.
What changes from the RTX 4070 12 GB to the RTX 4070 Ti Super 16 GB → · What changes from the RTX 4070 12 GB to the RTX 3090 24 GB →
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.2 5B on a RTX 4070 12 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
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), counting working memory and a small system reserve. The full 16-bit file needs about 13.8 GB.
Which Wan 2.2 5B file should I download for the RTX 4070 12 GB?
Q8_0 (5.4 GB) from QuantStack/Wan2.2-TI2V-5B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
Is FP8 faster than GGUF on the RTX 4070 12 GB?
It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.
How much do I need to download for Wan 2.2 5B on the RTX 4070 12 GB?
About 13.5 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 12 GB card, 32 GB of system RAM or more is recommended.