PrismML hopes its tiny LLM could change how we all use AI

Caltech startup PrismML released Bonsai 2 27B, a compressed version of the open Qwen3.8 27B model at 5.9 GB, 9–10 times smaller than the original. The model retains 98% of Qwen's benchmark scores and fits on a PC and a top-tier smartphone. The company raised $22.25 million in seed funding.

• Bonsai 2 27B compresses Qwen3.8 27B to 5.9 GB, 9–10 times less memory
• Retains 98% of Qwen's aggregate benchmarks versus 95% for the first Bonsai
• First Bonsai downloaded over 11 million times, smaller models another 2.6 million
• Startup raised $22.25 million from Khosla Ventures, Cerberus and Caltech