Poolside details Laguna S 2.1 base as a 118B MoE with 8B active params
cephaloform · x · 2026-07-22
Laguna S 2.1 base is the pre-trained model behind Laguna S 2.1, with 118B total parameters and about 8B active parameters per token.
- It uses interleaved full and sliding-window attention across 48 layers.
- The architecture includes 256 routed experts plus one shared expert.
- The base model is not publicly available; researchers can request access at [email protected].
- Poolside says the base model is not instruction-tuned and has no chat, reasoning, or tool-calling behavior; those capabilities live in Laguna S 2.1.
The post is mainly a model-card style announcement with concrete architecture details, not a product demo.
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