LongCat-Video: Meituan's Open-Source 13.6B Video Model

LongCat-Video is Meituan's open-source, MIT-licensed 13.6B video model for text-to-video, image-to-video and minute-long continuation at 720p/30fps. This guide covers what it does, the GPU memory it actually needs, how to install it, and how it benchmarks against Wan 2.2 and Veo3.

What is LongCat-Video?

LongCat-Video is an open-source video generation model from Meituan's LongCat team, released under the permissive MIT License. A single 13.6B-parameter model covers text-to-video, image-to-video, and video-continuation, and it is built for minute-long clips at 720p/30fps without the color drift that usually wrecks long generations.

It is a dense model (not mixture-of-experts). On Meituan's internal benchmark it scores competitively with other open models while approaching proprietary systems like Veo3 (see benchmarks below). Weights are published on Hugging Face.

Who it's for: teams and creators who want to self-host video generation — short-form clips, B-roll, or (via the avatar branch) audio-driven talking-head video — instead of paying per call for a closed API like Veo.

Can your GPU run it?

Short answer: not on a typical consumer card without quantization.

Meituan never published a minimum-VRAM number — the community has been asking since launch (issue #20, still open). What the field reports tell us:

So plan on a 48GB+ GPU for the full-precision model, or use a quantized build for 24GB-class cards. Multi-GPU inference is supported via context-parallelism, though some users report failures on 4 cards that worked on a single card (issue #27).

Install LongCat-Video

git clone --single-branch --branch main https://github.com/meituan-longcat/LongCat-Video
cd LongCat-Video
conda create -n longcat-video python=3.10 && conda activate longcat-video
pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu124
pip install ninja psutil packaging && pip install flash_attn==2.7.4.post1
pip install -r requirements.txt
huggingface-cli download meituan-longcat/LongCat-Video --local-dir ./weights/LongCat-Video

Generate your first video

Text-to-video on a single GPU:

torchrun run_demo_text_to_video.py --checkpoint_dir=./weights/LongCat-Video --enable_compile

Swap the script for other modes: run_demo_image_to_video.py, run_demo_long_video.py, or run_demo_interactive_video.py. Prefer a UI? Run streamlit run ./run_streamlit.py. For multi-GPU, add --nproc_per_node=2 --context_parallel_size=2.

How LongCat-Video compares

Meituan's internal Text-to-Video MOS evaluation (higher is better):

Overall Quality ↑LongCat-VideoWan 2.2 (open)Veo3 (proprietary)
MOS3.383.353.48

Among open-source models it edges out Wan 2.2 and lands within ~0.1 of Google's proprietary Veo3 — strong for a model you can self-host under MIT. On image-to-video it is weaker (3.17 overall, behind Seedance's 3.35).


Sources: official GitHub repo, Hugging Face model card, and the LongCat-Video Technical Report (arXiv:2510.22200). Compiled from official documentation and community reports; not independently benchmarked.

Get the weights on Hugging Face

FAQ

What GPU do you need to run LongCat-Video?
Meituan never published an official VRAM figure. Community reports show the 13.6B model is memory-hungry — one user hit out-of-memory on a 48GB GPU, and the community fast fork relies on 4/8-bit quantization to fit cards under 48GB. For 24GB consumer cards, plan on a quantized build.
Is LongCat-Video free for commercial use?
Yes. The model weights are released under the MIT License.
How long can the videos be?
Minutes. It is natively pretrained on video-continuation, so it extends clips without the color drift or quality collapse common to other models.
Can it generate audio-driven avatars?
Yes, via the LongCat-Video-Avatar 1.5 branch, which uses a Whisper-large-v3 audio encoder with INT8 quantization and distilled fast inference.

Last updated: 2026-06-29