Skip to content
Local AI Wizard
Your machine
Theme

Wan 2.2 vs HunyuanVideo for local video

Two open text-to-video models and the GPU memory they document

Facts from the reviewed catalog

Facts from the reviewed catalog
SpecificationWan2.2 T2V-A14BHunyuanVideo
TaskVideoVideo
Parameters27B13B
LicenseApache 2.0Publisher terms: Tencent Hunyuan Community License Agreement
Commercial useAllowedlicense textAllowed with conditionsNot licensed in the EU, UK or South Korea; over 100M monthly users needs a Tencent license · license text
Quality · LMArena 2026-09-22 · text-to-video1,132 ± 151,116–1,147 · 10,458 votes · rank 42 · sourceArena rated hunyuan-video-1.5; this entry is the first HunyuanVideo · source
Memorypublisher's documented path from 80 GB (CUDA, conditional)publisher's documented path from 45 GB (CUDA)
Checkpointofficial cardofficial card

Only Wan2.2 T2V-A14B has a result in LMArena 2026-09-22 · text-to-video (1,132 ± 15); HunyuanVideo has none, so the two are not ranked from this source and no score is inferred for it. Blind pairwise votes by people on hosted outputs, CC BY 4.0. A rating is relative; overlapping intervals mean the order is not settled. Scale: Arena rating ± half the confidence interval.

Memory on three machines

Each machine's own reserve is added (graphics cards 2 GB; unified and system memory 25%, 2 to 8 GB). Planning estimates, not measured runs.

Wan 2.2 vs HunyuanVideo for local video: memory on three machines
MachineWan2.2 T2V-A14BHunyuanVideo
RTX 4090 · 24 GB VRAM80 GBBelow the documented minimum45 GBBelow the documented minimum
RTX 5090 · 32 GB VRAM80 GBBelow the documented minimum45 GBBelow the documented minimum
DGX Spark · 128 GB unified80 GBWithin a conditional path (offload or quantization)45 GBWithin a conditional path (offload or quantization)

Wan2.2 T2V-A14B: publisher's documented path from 80 GB (CUDA, conditional). HunyuanVideo: publisher's documented path from 45 GB (CUDA). Formulas

Everything that runs on each machine: RTX 4090 · 24 GB VRAM · RTX 5090 · 32 GB VRAM · DGX Spark · 128 GB unified

Which to choose

Local video needs far more memory than images. Wan2.2 T2V-A14B (27 billion parameters in two experts, Apache 2.0) documents an 80 GB conditional path; HunyuanVideo (13 billion) documents 45 GB and 60 GB paths, and Tencent's licence excludes the EU, the UK and South Korea. None of the consumer cards below reaches either documented minimum. Wan 2.2 has a rating in the LMArena text-to-video release; HunyuanVideo has none, because the Arena rated HunyuanVideo 1.5, a later checkpoint.

Files and run commands

The default file of the most downloaded collected source, or the commands each card documents. Not run by this site.

Wan2.2 T2V-A14B

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Wan · model card · (1) Without Prompt Extension
python generate.py  --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --offload_model True --convert_model_dtype --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
Wan · model card · (1) Without Prompt Extension
torchrun --nproc_per_node=8 generate.py --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."

HunyuanVideo

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

HunyuanVideo · model card · Single-gpu Inference
cd HunyuanVideo

python3 sample_video.py \
    --video-size 720 1280 \
    --video-length 129 \
    --infer-steps 50 \
    --prompt "A cat walks on the grass, realistic style." \
    --flow-reverse \
    --use-cpu-offload \
    --save-path ./results
HunyuanVideo · model card · Parallel Inference on Multiple GPUs by xDiT
cd HunyuanVideo

torchrun --nproc_per_node=8 sample_video.py \
    --video-size 1280 720 \
    --video-length 129 \
    --infer-steps 50 \
    --prompt "A cat walks on the grass, realistic style." \
    --flow-reverse \
    --seed 42 \
    --ulysses-degree 8 \
    --ring-degree 1 \
    --save-path ./results
HunyuanVideo · model card · Run a Gradio Server
python3 gradio_server.py --flow-reverse

# set SERVER_NAME and SERVER_PORT manually
# SERVER_NAME=0.0.0.0 SERVER_PORT=8081 python3 gradio_server.py --flow-reverse

Numbers each publisher reports

Each card's own results with its own settings. Publishers choose different tests and settings, so these values are never compared across publishers here.

Wan2.2 T2V-A14B · reported by Wan-AI

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

HunyuanVideo · reported by Tencent Hunyuan

The publisher's card states no benchmark result for this checkpoint (read 2026-10-26). not published on the card · read 2026-10-26

Limits and dates

The published quality benchmark does not test a local quantized build. Memory estimates are not speed measurements or guaranteed hardware fits. Repository size, when available, is not VRAM. Formulas

Page updated · Catalog reviewed · LMArena 2026-09-22 · text-to-video