@cline: Laguna S 2.1 is a breakthrough in small model performance, beating models 3x its size. At only 118b param, it beats Dee…

X AI KOLs Following Models
model-release mixture-of-experts benchmark poolside laguna-s small-model

Summary

Poolside releases Laguna S 2.1, a 118B parameter Mixture-of-Experts model with 8B activated per token and 1M context window, claiming to beat models three times its size like DeepSeek v4 Pro, Gemini 3.6 Flash, and Thinking Machines Inkling.

Laguna S 2.1 is a breakthrough in small model performance, beating models 3x its size. At only 118b param, it beats DeepSeek v4 Pro, Gemini 3.6 Flash, and Thinking Machines Inkling on benchmarks. Try in Cline with model id: poolside/laguna-s-2.1
Original Article
View Cached Full Text

Cached at: 07/22/26, 02:18 AM

Laguna S 2.1 is a breakthrough in small model performance, beating models 3x its size.

At only 118b param, it beats DeepSeek v4 Pro, Gemini 3.6 Flash, and Thinking Machines Inkling on benchmarks.

Try in Cline with model id: poolside/laguna-s-2.1

Poolside (@poolsideai): 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 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

Similar Articles

Laguna S 2.1

Hacker News Top

Poolside releases Laguna S 2.1, a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token and up to 1M token context, achieving competitive scores on long-horizon coding benchmarks and touted as the most capable agentic coding model in its weight class.

poolside/Laguna-S-2.1-NVFP4

Hugging Face Models Trending

Poolside releases Laguna S 2.1, a 117.6B parameter Mixture-of-Experts model with 8.5B activated parameters designed for agentic coding, featuring sliding window attention, native reasoning support, and local deployment capability.

Introducing Laguna XS 2.1 (5 minute read)

TLDR AI

Poolside releases Laguna XS 2.1, a 33B parameter Mixture-of-Experts model with 3B activated parameters per token, designed for agentic coding, with improvements on SWE-bench Multilingual and other benchmarks, now available under the permissive OpenMDW-1.1 license.