All models

Wan / VIDEO

Wan 2.2 TI2V 5B VRAM requirements

Explore memory tradeoffs with sourced model data and transparent estimates.

FP8 estimate

17.4 GiB

at default settings

FP16 estimate

17.4 GiB

at default settings

Suggested GPU

1 × RTX 4000 Ada Generation 20 GiB

Model files & facts

Mediavideo
Default resolution1280 × 704
Default frames121
Temporal compression4
NotesEstimates the text-to-video workflow. The image-conditioned workflow also encodes a reference image.

Precision & offloading comparison

Source default resolution and frame count · batch 1 · FP16 text encoders · safety margin included.

BackboneText encodersTotal
FP16GPU17.41 GiB
FP16CPU17.41 GiB

ComfyUI file placement

Example component locations; install matching loader nodes. Brace patterns in source filenames denote all shards. Preserve the source layout when a loader requires it.

models/diffusion_models/split_files/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors
models/text_encoders/umt5_xxl_fp16.safetensors
models/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
models/vae/split_files/vae/wan2.2_vae.safetensors

Recommended GPUs by memory fit

FP16 backbone at source default resolution, FP16 text encoders on GPU. Smallest nominal memory first; green results only. Check backend and precision support separately.

Sources & verification

Hugging Face model card

Exact file sources are linked in the component table above. ComfyUI memory planner constant

Last verified: 2026-11-20

Try your configuration

Your workload

Custom diffusion model parameters

Uses the ComfyUI activation and decode profile for Wan 2.2 TI2V 5B. Leave fields empty to use catalog files. Placeholder counts approximate half-precision file sizes.

Your hardware

Output dimensions

Images or videos per batch. Serving concurrency and throughput require separate measurements.

Resolution and peak VRAM
Sampling and timing

One step is one scheduler iteration. Enter timings from the same device, batch, resolution and guidance settings. Fixed overhead includes encoding, decoding and other work outside sampling.

Advanced
Decode at full size
Off — text encoders stay on the GPU
Off — ComfyUI swaps models between stages; the peak stage counts

Performance and memory results

72.5%Memory use

Memory estimate

17.4 GiB needed

Fits6.6 GiB to spare24.0 GiB available

The estimated workload fits with the safety margin included.

Wan 2.2 TI2V 5B

RTX 4090 24 GiB

Model specifications
Memory breakdown · vae decode stage (peak)GiB

Vertical line = usable hardware memory

  • VAE1.31 GiB
  • VAE decode activations13.43 GiB
  • ComfyUI inference reserve0.80 GiB
  • Safety margin1.86 GiB

Per-stage peak

ComfyUI moves idle models to system RAM between stages; the largest stage sets the requirement. Totals include the safety margin.

  • Text encode12.75 GiB

    Text encoders (FP16) 10.59 + ComfyUI inference reserve 0.80

    Subtotal 11.39 + safety margin (12%) 1.37 ≈ 12.75 GiB

  • Sampling14.63 GiB

    Diffusion model (FP16) 9.31 + Sampling activations 2.95 + ComfyUI inference reserve 0.80

    Subtotal 13.06 + safety margin (12%) 1.57 ≈ 14.63 GiB

  • VAE decodePeak17.41 GiB

    VAE 1.31 + VAE decode activations 13.43 + ComfyUI inference reserve 0.80

    Subtotal 15.54 + safety margin (12%) 1.86 ≈ 17.41 GiB

Generation performance

Denoising steps
50
Conditioning branches per step
1
Latent patch tokens per sample
27,280
Estimated backbone work per step
547.132 TFLOP
Step time at single-device BF16 peak
3,311.937 ms

DiT work estimates cover linear layers and visual self-attention. Enter measured step time and fixed overhead under Sampling and timing.

Compare GPU capacity

Frequently asked questions

How much VRAM does Wan 2.2 TI2V 5B need?

Our default estimate at the source default resolution, batch 1, FP16 text encoders on GPU and FP16 backbone is 17.4 GiB including the safety margin. These are estimates, not measured guarantees.

Can I offload text encoders?

Yes. The CPU option removes text encoder weights from the GPU estimate, trading GPU memory for system RAM and transfer time. Each component still needs to fit on its assigned device.

Does a green result guarantee compatibility?

No. Green means the estimated memory including safety headroom fits. Backend support, precision support, kernels and runtime allocation can differ. Confirm compatibility and measure your actual workflow.

Where do these estimates come from?

Architecture and file sizes are traced to model sources. The precision table identifies measured GGUF rates, block storage and nominal bit widths. The source data for Wan 2.2 TI2V 5B was last verified on 2026-11-20. Memory estimates use GiB.