Poolside Releases Open-Weight Laguna S 2.1 Coding Model

Poolside develops AI systems for long-horizon software-engineering work, where agents must navigate repositories, use tools and complete tasks rather than merely suggest code. Laguna S 2.1 uses a sparse mixture-of-experts architecture to combine large-model capacity with lower inference demands. Its open weights and ability to run on a single NVIDIA DGX Spark broaden deployment options for developers and companies seeking to operate coding agents in their own environments.

Poolside released Laguna S 2.1 on July 21, 2026, with 118 billion total parameters and 8 billion activated per token, plus a 1,048,576-token context window. The company reported scores of 70.2% on Terminal-Bench 2.1, 78.5% on SWE-bench Multilingual and 59.4% on the public SWE-Bench Pro dataset. Weights are available on Hugging Face under the OpenMDW-1.1 license, alongside quantized variants intended to ease local deployment.