Model reference · open weights
Multics is an open-weight video model from TencentARC. Multics (BF16) weighs 29.9 GB; the smallest configuration that runs it is RTX 4090 24 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the TencentARC/Multics model card, 2026-10-13
What it is
| Released by | TencentARC |
|---|---|
| Released | 2026-10-12 |
| VRAM | 29.9 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB | does not fit | |
| RTX 3090 24 GB | fits (encoders offloaded) | 23.4 GB |
| RTX 4090 24 GB | fits (encoders offloaded) | 23.4 GB |
| RTX 5090 32 GB | tight | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Multics enables scalable multi-player video generation through hierarchical communication.
Project page · Code and instructions
This repository contains the complete 4-player Multics DiT checkpoint, its configuration, the Wan2.2 VAE, the UMT5 text encoder, and tokenizer. The same checkpoint supports 6-, 8-, and 10-player generation without retraining.
From the Multics code repository, download all inference weights with:
hf download TencentARC/Multics --local-dir models
Then generate the first 4-player example:
python inference.py --config configs/inference_demo.yaml \
--checkpoint models/multics/4players/checkpoints/model.ckpt \
--hparams models/multics/4players/hparams.yaml \
--case 1
See the code repository for installation, example inputs, and scalability commands.
The weights are distributed under the Apache 2.0 license. See LICENSE and THIRD_PARTY.md for component attribution.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works
Running it yourself
Rent a machine by the hour. How to run this model is on its model card.