X · @huggingface
· X / Twitter
RT Poolside: Today we're releasing Laguna S 2.1, our most capable model to date. It's a 118B total parameter Mixture-of-Experts model with 8B activate…
RT PoolsideToday we're releasing Laguna S 2.1, our most capable model to date.It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes.Capable enough to hold its own against models many times its size. Small enough to run o