Poolside opens Laguna S 2.1, a 118B coding model with 1M context
AccBalanced · x · 2026-07-22
Poolside released Laguna S 2.1, its most capable model so far: a 118B total-parameter sparse MoE with 8B active per token, up to 1M context, and thinking/no-thinking modes. The team says it is built for agentic coding and long-horizon work, can run on a single NVIDIA DGX Spark in official NVFP4 quantized form, and is already supported by vLLM out of the box.
Related event: Poolside Releases 118B Open-Weight Coding Model Laguna S 2.1(35 posts)→
More from coding & agent
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents — AlishaOutridge · 2026-09-11
- Gergely Orosz: Shipping 10x PRs With AI Agents, Sites Fill With Small Regressions — ducha_aiki · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11