#runllama

Meta Llama 4 Maverick is a free 400B open-weight model with a 10M context window that rivals GPT-5.4. Full guide: benchmarks, setup, and real-world use cases.

Meta’s Llama 4 Scout launched April 2026 with a 10M token context window. Here’s the hardware specs, vLLM setup, and benchmark breakdown for local deployment.