What GPU do I need to run Wan-AI/Wan2.2-TI2V-5B-Diffusers?
A 5B-parameter text/image-to-video model that runs on a consumer 4090. 5.0B parameters, published in F32. View on Hugging Face
Wan2.2-TI2V-5B-Diffusers is published by Wan-AI on Hugging Face, with 189,587 downloads and 160 likes to date. It's a unlisted-architecture model built for text-to-video, published natively in F32.
What Wan2.2-TI2V-5B is
Wan2.2-TI2V-5B is Wan-AI's hybrid text-and-image-to-video model, built with the Wan2.2-VAE (a 16×16×4 compression ratio). Its own model card states it supports both text-to-video and image-to-video generation at 720P/24fps and can run on a single consumer-grade GPU such as an RTX 4090, and describes it as one of the fastest 720P@24fps models available.
License note: fully permissive, no gating and no usage restrictions. Facts in this section are sourced from Wan2.2-TI2V-5B's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Text-to-video and image-to-video generation at 720P/24fps
- Video generation on a single consumer-class GPU
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 18.6 GB | 22.4 GB | RTX A5000 | 1 | $0.176/hr |
| FP8 (quantized) | 4.7 GB | 5.6 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 2.3 GB | 2.8 GB | RTX 5060 Ti | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Wan2.2-TI2V-5B-Diffusers at its published (F32) precision: 1× RTX A5000, at $0.176/hr per GPU ($0.176/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Wan2.2-TI2V-5B-Diffusers: common questions
Does Wan2.2-TI2V-5B-Diffusers fit on a 24 GB GPU?
Yes. At FP32 it needs 22.4 GB of VRAM, so a 24 GB card holds it with 1.6 GB to spare. A 16 GB card is not enough for it at FP32.
Can Wan2.2-TI2V-5B-Diffusers run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 18.6 GB, or 22.4 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 9.3 GB, or 11.2 GB with overhead. That moves it onto a 12 GB card instead of a 24 GB one. How much accuracy the cast costs is model-specific and is not measured here.
What is the least VRAM Wan2.2-TI2V-5B-Diffusers can run in?
2.8 GB, at INT4 (quantized), which fits a 6 GB card, against 22.4 GB at FP32. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing Wan2.2-TI2V-5B-Diffusers lower the GPU bill?
Yes. At FP32 the cheapest live fit is one RTX A5000 at $0.176/hr. At FP8 (quantized) it drops to one RTX 5060 Ti at $0.110/hr, provided a quantized checkpoint exists for it.
How to run Wan2.2-TI2V-5B
Run Wan2.2-TI2V-5B with Diffusers (Python)
From Wan-AI/Wan2.2-TI2V-5B-Diffusers's own model card (requires diffusers installed from source as of this model's release).
import torch
from diffusers import WanPipeline, AutoencoderKLWan
from diffusers.utils import export_to_video
model_id = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
pipe.to("cuda")
output = pipe(prompt="a description of the scene", height=704, width=1280, num_frames=121).frames[0]
export_to_video(output, "ti2v_out.mp4", fps=24)Source: https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers/raw/main/README.md
Run Wan2.2-TI2V-5B with ComfyUI
Aquanode's ComfyUI template comes with ComfyUI preinstalled, and lib/pods/catalog.ts's comfyui-wan-video first-party pod uses this same checkpoint. Download Wan-AI/Wan2.2-TI2V-5B's checkpoint into the models folder and load it in a workflow.
Deploy Wan2.2-TI2V-5B on Aquanode
Aquanode has no one-click deploy template for Wan2.2-TI2V-5B; it comes with ComfyUI preinstalled, so you only need to load the checkpoint, not install anything. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch the ComfyUI template sized to the requirement above (1× RTX A5000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch the ComfyUI templateWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Wan2.2 models
- LongLive-2.0-5B-Diffusers (5.0B, BF16)
- Wan2.2-T2V-A14B-Diffusers (14.3B, F32)
- Wan2.2-I2V-A14B-Diffusers (14.3B, F32)
- Wan2.2-I2V-A14B-Lightning-Diffusers (14.3B, BF16)
- Wan2.2-S2V-14B (16.3B, BF16)
Related reading: RTX A5000 pricing and specs, The NVIDIA Inception program, explained, Google Colab alternatives for dedicated GPU access, Free GPU credits for students and researchers, and RunPod volume disk vs. network volume, compared.
