Click anywhere on an image or video → instant object segmentation. Apache 2.0. Universal segmentation model used in medical imaging, autonomous driving datasets, and content creation. Zero training required for any object class.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 6GB VRAM Recommended
The SAM 2 model by Meta AI is a 300M parameter architecture optimized for vision tasks. It requires approximately 4GB of VRAM to comfortably run locally using a FP16 quantization. Extending the context window up to 0 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running SAM 2 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 6GB of VRAM to run the FP16 quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run sam2' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.