Poolside releases Laguna S 2.1 with 118B MoE, 1M-token context and open weights
nathanbenaich · x · 2026-07-22
Poolside says it has released Laguna S 2.1, its most capable model yet.
- 118B total parameters with 8B activated per token (MoE).
- Supports up to 1M-token context.
- Includes both thinking and non-thinking modes.
- The company says it can compete with models many times larger while still running on a single NVIDIA DGX Spark.
- Weights are available now under OpenMDW-1.1 on Hugging Face.
Related event: Poolside Releases 118B Open-Weight Coding Model Laguna S 2.1(35 posts)→
More from Infra
- 12 KV Cache Reduction Techniques Every AI Engineer Should Understand, Explained — blaizedsouza · 2026-09-11
- The shadow GPU capacity market is formalizing, with Meta selling excess compute to outside buyers — DavidLinthicum · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- 80% of the DIY LLM inference hype posters have already quit — it's brutally hard systems work — abhijithneil · 2026-09-11
- Hugging Face's Ultra Scale Playbook: a free book on training LLMs on GPU clusters — mdancho84 · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11