AINewsnow

Serving Groot-19B-A3B at 256K on one RTX 5090: the memory budget and the thinking trap

GrootTeam says its Groot-19B-A3B holds a 256K-token context on one RTX 5090, and labels that figure an estimate from memory sizes. A token is a word piece, and the context is how much text the model can see at once. We wanted a measurement, so we deployed the 20.9 GB FP8 build (weights stored in 8…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-12 06:37 · DEV Community — AI
    Serving Groot-19B-A3B at 256K on one RTX 5090: the memory budget and the thinking trap

More stories

  1. The phantom life of Alice Huang, alleged Chinese spy who had affair with Nvidia CEO — CSET Georgetown
  2. Google's Gemini 4 Carbon rolls out to Pro plan users as n8n adds model support — Google DeepMind Blog
  3. Anthropic IPO Said to Be Multiple Times Oversubscribed as AI Trade Rebounds — CNBC Technology
  4. ByteDance plans Muse-like AI assistant launch within weeks, Bloomberg reports — Techmeme
  5. Anthropic launches Claude Fable 5.2 with lower pricing and top benchmark scores — Anthropic (X)
  6. Google launches Gemini Decisions API with Gemini Decision 1 model — Google Cloud AI Blog
  7. AWS releases local emulator written entirely by autonomous AI agents — AWS Machine Learning Blog
  8. Google DeepMind launches AlphaGenome 2 to predict DNA variant effects across cell types — Google DeepMind Blog

Get the daily brief of stories like this at 6:30 every morning →