3 sources covering

TML releases Inkling 2 Mini, an open-weights 26.4B-parameter transformer that loops middle layers three times per token for better reasoning with fewer tokens (Thinking Machines Lab)

Techmeme ·

Read at Techmeme

How outlets word it

The words in 3 outlets' headlines on this story, compared word by word. It shows differences in wording, not which is right.

Most outlets sayInklingMiniMachinesreleasesThinking

Words only one outlet used

  • TML releases Inkling 2 Mini, an open-weights 26.4B-parameter transformer that loops middle layers three times per token for better reasoning with fewer tokens (Thinking Machines Lab)

    Techmeme

  • Thinking Machines Releases Inkling 2 Mini for Local AI

    The Defiant

Who's covering it

Order

First reported by Hacker News at · 3 outlets in all

Filter by type, country or lean
By type
Country
  1. TechmemeTML releases Inkling 2 Mini, an open-weights 26.4B-parameter transformer that loops middle layers three times per token for better reasoning with fewer tokens (Thinking Machines Lab)
  2. The DefiantThinking Machines Releases Inkling 2 Mini for Local AIThe roughly 20GB model supports Apple silicon devices with 32GB or more memory. Its Apache 2.0 listing comes with a separate acceptable-use policy.
  3. Hacker NewsInkling 2 Mini