Holds the record for largest context window of any open-weight model at 10 million tokens — enough for an entire codebase. MoE architecture means only 17B parameters are active per forward pass.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 50GB VRAM Recommended
The Llama 4 Scout model by Meta AI is a 109B (MoE) parameter architecture optimized for chat tasks. It requires approximately 48GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 10,000,000 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running Llama 4 Scout 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 50GB of VRAM to run the Q4_K_M quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run llama4-scout' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.