FULL STORY

Poolside Releases Laguna S 2.1 Open-Weights Coding Model

Poolside released Laguna S 2.1, a new open-weights coding model designed for agentic programming, which subsequently launched on Nous Portal with a two-week free trial.

2026-07-22 ~ 2026-07-22 · 2 episodes · 29 posts

Episode 1 · Poolside Releases 118B Open-Weight Coding Model Laguna S 2.1 (2026-07-22, 27 posts)

Poolside has launched Laguna S 2.1, its latest open-weight coding model, focusing on agentic coding and long-horizon tasks. The model supports a context length of up to 1 million tokens. The company emphasizes its stable performance in long-chain tasks, noting that its agentic coding capabilities surpass some larger models.

Key Details

Laguna S 2.1 utilizes a MoE (Mixture of Experts) architecture with a total of 118B parameters, activating 8B parameters per token. Released under the OpenMDW license, its open weights are well-suited for extended autonomous operations by local coding agents. In terms of performance, official benchmarks reveal leading scores on tests like Terminal-Bench 2.1. Additionally, NVIDIA shared and endorsed the model, acknowledging its ability to pack strong capabilities into a compact size.

7 more related posts →

Episode 2 · Poolside's Laguna S 2.1 Available on Nous Portal with Two-Week Free Access (2026-07-22, 2 posts)

Nous Research announced that poolside_ai's latest model, Laguna S 2.1, is now available on Nous Portal. Users can access the model with two weeks of free inference services.