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
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11