DownloadLaguna M.1 is Poolside’s flagship Mixture-of-Experts model built specifically for agentic coding, software engineering, and long-horizon autonomous workflows. It contains approximately 225.8B total parameters with 23.4B activated per token, making it substantially larger and more capable than Laguna XS.2 while maintaining efficient inference through sparse activation. Trained from scratch on roughly 30 trillion tokens using Poolside’s in-house “Model Factory” pipeline, the model focuses on complex software development tasks, repository-scale reasoning, tool use, and multi-step agent execution. Laguna M.1 was designed to compete with leading frontier coding models on benchmarks such as SWE-Bench, Terminal-Bench, and other agentic engineering evaluations. It supports reasoning, tool calling, and long-context workflows, making it suitable for autonomous coding agents, software maintenance, debugging, and large-scale development projects.
Features
- 225.8B-parameter Mixture-of-Experts architecture
- 23.4B active parameters for efficient inference
- Built specifically for agentic coding workflows
- Trained from scratch on approximately 30 trillion tokens
- Strong performance on SWE-Bench and Terminal-Bench tasks
- Supports long-horizon multi-step reasoning and execution
- Designed for tool use and autonomous software engineering agents
- Developed using Poolside’s integrated “Model Factory” training system
Project Samples
