Poolside Releases Laguna S 2.1: Small Parameters Rivaling Larger Models
cephaloform · x · 2026-07-22
Poolside has released the Laguna S 2.1 model. With 118B total parameters and 8B active parameters per token, it is designed to run on a single NVIDIA DGX Spark.
The model reportedly delivers performance comparable to much larger models on agentic coding tasks and exhibits remarkable persistence across long-horizon tasks. Additionally, benchmarks indicate it achieves near-GLM performance on deepswe with only about 1/7th of the parameter count.
Related event: Poolside Releases Laguna S 2.1: 118B Open-Weight Coding Model(28 posts)→
More from Models
- Grok 4.5 is being pitched as a one-person game studio — minchoi · 2026-07-22
- Laguna S 2.1 matches GLM-5.2 on game coding with 6x fewer parameters — rohanpaul_ai · 2026-07-22
- Open source is now challenging the AI duopoly, with Kimi K3 first in line — bindureddy · 2026-07-22
- A January 2025 pretraining cutoff is “mind-boggling” for a small-compute model — _arohan_ · 2026-07-22
- Qwen3.8 preview brings Alibaba’s open-weight push to enterprise distribution — krishnan · 2026-07-22
- Google reportedly dropped a couple of models today, with more launches teased — bindureddy · 2026-07-22