Love this scrappy project. Hoping more US labs follow suit, showing they can also make solid models with small focused teams. This also intellectually follows on the olmo lineage, so super cool to see what our baby looks like scaled up.
Nathan Lambert praises Ricursive's Ripple-65B Preview as a small-team US open model
AINathan Lambert praises Ricursive Intelligence's scrappy project and hopes more US labs will show that small focused teams can build solid models. He says the work follows the OLMo lineage and is interested in how it scales up.
Nathan LambertVerified on X
@natolambert
Today we release Ripple-65B Preview, our 65B dense LLM we pretrained from scratch. Ripple sets a new state-of-the-art for U.S. open-weight models in agentic coding tasks, surpassing significantly larger models including Muse Spark Open-816B, Beam-501B, Inkling-975B, and Nemotron 3 Ultra-550B. Learn more: https://www.ricursive.com/ripple
Source details
Nathan Lambert · x.comPublished · added here
Original title: Love this scrappy project. Hoping more US labs follow suit, showing they can also make solid models with small focused teams. This also i...