Poolside’s Laguna S 2.1 brings 118B parameters and 1M context to a single DGX Spark
ying11231 · x · 2026-07-22
- The post highlights Laguna S 2.1 from poolsideai, now live on SGLang with day-0 support.
- It has 118B total parameters, a 1M context window, and both thinking and no-thinking modes.
- The model is positioned for long-horizon agentic coding: it reportedly keeps planning, testing, and self-correcting for up to 24 hours with little intervention.
- Efficiency comes from sparse MoE design: only 8B active parameters per token, plus official NVFP4 quantization that fits the model on a single NVIDIA DGX Spark.
- Reported scores include 70.2% on Terminal-Bench 2.1 and 78.5% on SWE-bench Multilingual.
Related event: Poolside Releases 118B Open-Weight Coding Model Laguna S 2.1(35 posts)→
More from Models
- 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
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27