Subquadratic — Introducing SubQ: The First Fully Subquadratic LLM

Subquadratic is a frontier AI research and infrastructure company building a new class of LLMs.

Subquadratic — Introducing SubQ: The First Fully Subquadratic LLM Product Introducing SubQ: The First Fully Subquadratic LLM By Justin Dangel, co-founder and CEO, Subquadratic Date May 5, 2026 Transformers defined the last decade of AI — the "T" in ChatGPT. They unlocked modern language understanding, reasoning, and much of what we now think of as AI. Yet one fundamental limitation has shaped everything built on top of them: compute requirements scale quadratically with context length. In practice, longer inputs don't reliably improve how well a model uses the information provided. As context

saved by

• Varun Goyal

related reading

• Subquadratic — How SSA Makes Long Context Practicalsubq.ai
• google seeming solved efficient attentionceselder.substack.com
• Small Models Have Arrivedcalv.info
• Recursive Language Models | Alex L. Zhangalexzhang13.github.io
• The Big LLM Architecture Comparisonmagazine.sebastianraschka.com
• On the Tradeoffs of SSMs and Transformers | Goomba Labgoombalab.github.io
• GenAI Handbookgenai-handbook.github.io
• [2507.04239] Scaling Context Requires Rethinking Attentionarxiv.org
• Memory makes computation universal, remember?thinks.lol
• Latency Scaling Differences for GPT and Claude Modelsepoch.ai
• Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
• Reiner Pope – The math behind how LLMs are trained and serveddwarkesh.com