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 118B Open-Weight Coding Model Laguna S 2.1(35 posts)→
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Custom VQA benchmark under 48GB VRAM: Qwen3.8-Flash-Next leads, Qwen3.8-27B regressed — EmilPi · 2026-10-27