Full open-source Sora replication — weights, training code, and full data pipeline are all public. The most transparent video generation model. Essential for researchers studying text-to-video architectures and training dynamics.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 18GB VRAM Recommended
The Open-Sora model by HPC-AI Tech is a 4B video parameter architecture optimized for video tasks. It requires approximately 16GB of VRAM to comfortably run locally using a BF16 quantization. Extending the context window up to 0 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running Open-Sora at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 18GB of VRAM to run the BF16 quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run open-sora' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.