Model reference · open weights
WorldCrafter is an open-weight video model from TencentARC. WorldCrafter-Base (FP32) weighs 29.2 GB; the smallest configuration that runs it is RTX 5090 32 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the TencentARC/WorldCrafter-Base model card, 2026-10-01
What it is
| Released by | TencentARC |
|---|---|
| Released | 2026-09-21 |
| Parameters | 14.3B |
| VRAM | 29.2 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4090 24 GB | does not fit | |
| 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
Base transformer weights and their matching camera adapter and LoRA for the WorldCrafter inference code.
Place this directory beside WorldCrafter-Fast. Base reads the following shared folders from Fast: repencoder/, text_encoder/, tokenizer/, vae/, and scheduler/. Base does not need Fast's transformer or adapter folders. The relative path is configured in inference_config.json.
From the code repository root:
python inference.py --model-type base --model-path weights/WorldCrafter-Base --output-path outputs/base.mp4
Keep the Base-specific transformer/ and adapter/ together. SHA256SUMS covers the packaged Base files; shared component hashes are recorded in Fast's package.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. How to run this model is on its model card.