laguna-s-2.1

Laguna S 2.1

Laguna S 2.1 is a 118B-parameter Mixture-of-Experts model with approximately 8B parameters activated per token, designed for agentic coding and long-horizon work.

Highlights

• Agentic coding: optimized for software engineering, terminal tasks, and long-running tool workflows.
• Efficient MoE architecture: routes each token through 10 of 256 experts plus one shared expert.
• Native reasoning: supports interleaved and preserved thinking across tool calls.
• Long context: supports up to 262,144 tokens.