How to run Open-Sora 2.0 locally

HPC-AI Tech · Text → video · 11B params · Apache-2.0 (commercial OK)

A fully open 11B model (weights, code, and training recipe) trained for ~$200k that nearly closed the VBench gap with closed Sora, a landmark for reproducible open video AI.

What it costs to run — $0 markup

• On your own machine — $0. Runs free if you have about 24 GB of VRAM (~24GB-class with offload; 256px and 768px, supports both T2V and I2V), via ComfyUI / Diffusers.
• Rent a GPU — from $0.49/hr. Fits RTX A6000 48GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
• Download the weights — free. Open weights at hpcai-tech/Open-Sora-v2.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Get Open-Sora 2.0 on Hugging Face →

More video models

• Wan2.2 T2V-A14B — Text → video, ~24 GB VRAM
• Wan2.2 I2V-A14B — Image → video, ~24 GB VRAM
• HunyuanVideo — Text → video, ~45 GB VRAM
• Wan2.2 TI2V-5B — Text → video, ~8.0 GB VRAM
• LTX-Video (13B) — Text → video, ~13 GB VRAM
• CogVideoX-5B — Text → video, ~5.0 GB VRAM

Browse: all media models · chat / LLM models

Open the free Spanvero advisor → · We point you to the open weights + your own accounts, $0 markup, never resell compute. © 2026 Cynosure LLC.