Poolside releases Laguna S 2.1 — an open-weight coding model that punches 10x above its size

On July 21, 2026, Poolside released Laguna S 2.1, a 118B-parameter (8B active) open-weight mixture-of-experts coding model with up to a 1M-token context window that the company reports matching or beating much larger models on SWE-Bench Pro and Terminal-Bench 2.1 — trained in under four weeks on 4,000 H200s and runnable on a single NVIDIA DGX Spark. It landed on Vercel's AI Gateway the same day, including a free 256K-context tier.

What it means A single-GPU-runnable open model competitive on real coding benchmarks lowers the hardware and cost bar for self-hosting a capable coding agent instead of paying frontier-API prices — and there's a free tier to try it today.