AINewsnow

35 B MoE runs under 3 GiB RAM

This story is from 2026-09-22. It is preserved in the archive; the latest stories are on the live feed.

Learned routing slashes the active memory of a 35‑billion‑parameter Mixture‑of‑Experts model to under 3 GiB, turning laptop‑scale inference from fantasy into practice. By predicting which experts will be needed one token ahead, the engine streams only the relevant weights from SSD and never holds t…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-09-22 05:00 · DEV Community — Machine Learning
    35 B MoE runs under 3 GiB RAM

More stories

  1. Election backlash against data centers rattles AI stocks and expansion plans — TechCrunch AI
  2. Anthropic strikes $3.4bn deal for gas-fired generators to power AI data centres — Financial Times AI
  3. OpenAI to keep expanding AI data centers despite election results favoring restrictions — DigiTimes Asia
  4. Tencent AI chief warns AI will soon master biology, raising new safety risks — SCMP China Tech
  5. Apple's John Ternus reportedly pushing for faster AI progress beyond Siri upgrades — Techmeme
  6. US AI Safety Center Staff Now Report to White House, Raising Independence Concerns — AP News
  7. US voters reject AI data centers in nearly all local ballot measures — GeekWire
  8. Dev News Digest: 6 Nov 2026, 06:00 — DEV Community — AI

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