Poolside Releases Laguna S 2.1 Open-Weight Coding Model

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.

2026-07-22 ~ 2026-07-22 · 10 related posts

• Poolside launches Laguna S 2.1 with 118B parameters and 8B active per token — Madisonkanna · 2026-07-22
• [source] Poolside’s Laguna S 2.1 launches as a 118B open-weight MoE with 1M context — NVIDIAAI · 2026-07-22
• Poolside’s laguna s 2.1 claims 118B MoE, 1M context, and 78.5% on SWE-bench Multilingual — ben_burtenshaw · 2026-07-22
• Poolside releases Laguna S 2.1, a 118B open-weight coding agent with 1M context — ben_burtenshaw · 2026-07-22
• [source] Poolside launches Laguna S 2.1, a 118B MoE with a 1M-token context window — Lowkey_LokiSN · 2026-07-22
• Poolside releases Laguna S 2.1, a 118B open-weight coding model with 1M context — Every-Walrus · 2026-07-22
• Poolside says Laguna S 2.1 is a 118B open-weight agentic coding model with 1M context — GavinSBaker · 2026-07-22
• Poolside Releases Laguna S: An 118B Parameter Open-Source Model — Madisonkanna · 2026-07-22
• [source] Poolside Releases Laguna-S-2.1 Model, Tops Hugging Face Trending — poolside · 2026-07-22
• Poolside Releases Laguna S 2.1: A Small Coding Model Outperforming 1T+ Parameter Giants — mervenoyann · 2026-07-22