Sourced News

Atom Brief

Thu, Jul 16, 2026 · 0 stories · Confirmed · Subscribe
TECH

Mira Murati's Lab Publishes A Free 975-Billion-Parameter Language Model

Inkling activates 41 billion of 975 billion parameters per token, trained on 45 trillion multimodal tokens, hosted free on Hugging Face.

  • Total parameters: 975 billion; only 41 billion activate per token in this mixture-of-experts design.
  • Pretrained on 45 trillion tokens of text, images, audio and video; context reaches 1 million tokens.
  • The lab's own words: Inkling is not the strongest model available today, open or closed.

Why it matters: Free weights on a model the maker admits is not the best still buy users, data, and mindshare.

Thinking Machines Lab, "Inkling: Our Open-Weights Model" ↗ · Jul 15, 20267/15/26 · ✓ Checked✓ Check

Join the community.

Every story checked against the primary document.