1.2K views · 16 likes · 1 reposts (at collection)
Ricursive AI Releases Ripple-65B Preview, a Dense Model Trained From Scratch
- Who
- Nathan Lambert
- What
- praised Ricursive AI’s Ripple-65B Preview and its small-team approach to building solid models
- Quote
Love this scrappy project.
What happened
Ricursive AI says it has released Ripple-65B Preview, a 65B dense LLM pretrained from scratch. The company claims Ripple sets a state of the art for US open-weight models on agentic coding tasks, surpassing several larger models. Nathan Lambert praises the project and connects it to the OLMo lineage.
Why it matters
Lambert frames the release as an example of a small, focused US team producing a solid model, while connecting the project intellectually to the OLMo lineage.
Read next
See the full storyRicursive AI Releases Ripple-65B Preview, Nathan Lambert Praises the ProjectLove 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. https://t.co/xmuhpASWmW
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 https://t.co/0Dwh57Rr0JView the quoted post on X
The story so far
Ricursive AI says it has released Ripple-65B Preview, a 65B dense language model pretrained from scratch. The company claims it sets a state of the art among US open-weight models on agentic coding tasks, surpassing several larger models. Nathan Lambert praised the project as a scrappy effort and said he hopes more US labs will show they can build solid models with small, focused teams. He also connected Ripple to the OLMo lineage.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-11-04