Best Open-Weight LLMs by Memory Required (July 2026)

A new ranking of open-weight large language models by memory requirements as of July 2026 shows that the most memory-efficient models include Microsoft's Phi-4-mini at 3.8 GB and Google's Gemma 2 2B at 2.5 GB, while the largest models such as Meta's Llama 4 405B require over 800 GB of memory.