Poolside launches Laguna S 2.1, a 118B open-weight MoE with 1M context

Dan_Jeffries1 · x · 2026-07-22

Poolside releases Laguna S 2.1, an open 118B MoE model with 1M context

Poolside says Laguna S 2.1 is its most capable model yet: a 118B total-parameter Mixture-of-Experts model with 8B activated per token, up to 1M tokens of context, and both thinking and non-thinking modes.

The attached benchmark image shows Laguna S 2.1 slightly ahead of Claude Sonnet 5 and Qwen3.7-Max on the listed SWE-bench Multilingual chart.

Related event: Poolside Releases Laguna S 2.1: 118B Open-Weight Coding Model(31 posts)→

Original post →

More from Models

Models channel →