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.

Article URL: https://claude.ai/public/artifacts/4b74e194-a4b2-414f-a313-8d4b98a92b0b Comments URL: https://news.ycombinator.com/item?id=49044520 Points: 2 Comments: 0