Noesion Radarnoesion.ai
Release2026-08-03

Poolside released Laguna S 2.1, a freely licensed coding model sized between its existing small and large versions. It can hold about a million words of text at once and is built for long software tasks that involve calling tools repeatedly. Running it in full precision needs several high-end GPUs, though compressed versions and hosted access are available.

What changed

Poolside's openly licensed Laguna line offered a smaller 33B model and a much larger 225B one, with nothing in between.

What it unlocks

Running a coding-focused model that can hold about a million words of code and context in view, on a company's own hardware, for commercial use without licence fees.

  • 118B total parameters, ~8B active per token
  • 1,048,576-token context window
  • 70.2% on Terminal-Bench 2.1, 78.5% on SWE-bench Multilingual
  • roughly 236GB of weights at full precision
  • 89,270 downloads last month

What you need to act on it

  • multiple GPUs, or a compressed variant for smaller setups
  • or access through a hosted provider such as OpenRouter, Vercel AI Gateway or Ollama

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.