Llama 3.1 405B

Llama 3.1 405B is Meta's flagship open-weight large language model with 405 billion parameters and a 128k-token context window, designed for multilingual dialogue, reasoning, math, coding, and tool use. It is the largest model in the Llama 3.1 family and was positioned by Meta as the first openly available model competitive with top proprietary AI models on general-knowledge and instruction-following benchmarks. Source: supabase.