Skip to content
Local AI Wizard
Your machine
Theme

HunyuanVideo

Tencent Hunyuan · tencent/HunyuanVideo

Weights license: Publisher terms: Tencent Hunyuan Community License Agreement · code and components may use other terms

QualityNo public, reusable benchmark result covers this model.No comparable score
Published repository size39.8 GBAll published files · not runtime memory
Parameters13 Bmanufacturer model card
Published components3Listed in the model card

Quality

No comparable score

No public, reusable benchmark result covers this model.

Reported by the publisher

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

Runs on

Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.

Plan memory for this model

Consider it for

Consider HunyuanVideo from Tencent Hunyuan for the text-to-video task (13B parameters). 60 GB GPU memory at 1280×720 for 129 frames; 45 GB at 960×544 for 129 frames.

Check first

NVIDIA CUDA is required; the official project recommends an 80 GB GPU and tested Linux.

Measured speed

No published measurement for this checkpoint

Generation time per clip is shown only when a source publishes it with hardware, build and setup. It is never estimated.

How to run

60 GB GPU memory at 1280×720 for 129 frames; 45 GB at 960×544 for 129 frames. NVIDIA CUDA is required; the official project recommends an 80 GB GPU and tested Linux. Official hardware evidence

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

Evidence level: Publisher documentation linked; no execution reproduced by this site.

Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
tencent/HunyuanVideo
Task and modality
text-to-video · video
Count and basis
13B · manufacturer model card
Released
Tencent-Hunyuan/HunyuanVideo README (GitHub), News · read 2026-10-09source
Published repository size
39.8 GBNot runtime memory or a minimum download.files
Published components
13B diffusion transformer · 3D VAE · Text encoder
Runtime and precision
No local execution verified.
Commercial use
Allowed with conditions Not licensed in the EU, UK or South Korea; over 100M monthly users needs a Tencent license · Tencent Hunyuan Community License (tencent/HunyuanImage-3.0 LICENSE) · read 2026-10-18license text

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-22.