Can the RTX 5090 32 GB run Wan 2.2 I2V A14B?
Download FP8 (14.3 GB). With the model's working memory it needs about 18.6 GB, leaving 13.4 GB spare on 32 GB. Quality: practically identical to the original.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors high-noise model (early steps) FP8 · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/diffusion_models | 14.3 GB | Download → |
| Model | wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors low-noise model (late steps) FP8 · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/diffusion_models | 14.3 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_2.2_ComfyUI_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 35.6 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: 48 GB or more. ComfyUI keeps the model files, 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 35.6 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 41.6 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 I2V file on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 28.6 GB | 32.9 GB | spills 0.9 GB | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 14.3 GB | 18.6 GB | fits · 13.4 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · QuantStack | 15.4 GB | 19.7 GB | fits · 12.3 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 12.0 GB | 16.3 GB | fits · 15.7 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 10.8 GB | 15.1 GB | fits · 16.9 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 9.7 GB | 14.0 GB | fits · 18.0 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 7.2 GB | 11.5 GB | fits · 20.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 5.3 GB | 9.6 GB | fits · 22.4 GB spare | heavy loss; a last resort | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 3.5 GB working memory for this model + 0.8 GB kept free for the system. Wan 2.2 A14B uses two files of this size (high-noise and low-noise); only one sits in VRAM at a time, both must fit in system RAM.
03The text encoder
UMT5-XXL + CLIP Vision H: 11.4 GB as 16-bit, 6.7 GB as FP8, 3.7 GB as GGUF Q4_K_M (plus CLIP Vision H (1.3 GB) for the input image). 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 32 GB the FP8 encoder fits on its own, so prompt encoding stays fast.
04About this GPU
The RTX 5090 32 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
RTX 5090 32 GB: 32 GB GDDR7 · 512-bit · 1792 GB/s · Blackwell. Everything that runs on the RTX 5090 32 GB →
05What more VRAM would change
Nothing to gain for this model: the RTX 5090 32 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.
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.2 I2V on a RTX 5090 32 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does Wan 2.2 I2V need?
Around 9.6 GB with the smallest file (Q2_K) and 18.6 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 32.9 GB.
Which Wan 2.2 I2V file should I download for the RTX 5090 32 GB?
FP8 (14.3 GB) from Comfy-Org/Wan_2.2_ComfyUI_Repackaged.
Is FP8 faster than GGUF on the RTX 5090 32 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 I2V on the RTX 5090 32 GB?
About 35.6 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 32 GB card, 48 GB of system RAM or more is recommended.