Skip to content
NewA calmer, faster ZeroHour

Thinking Machines introduces Inkling 2 Mini, a 26B looped MoE

Original title: Meet Thinking Machines Inkling 2 Mini: 26B Looped MoE Runs on a 32GB Mac

MarkTechPostby Asif Razzaq ()14 min read
Part of a story covered by 6 sourcesThinking Machines releases Inkling 2 Mini; GGUF builds followMerged summary & timeline
AI summary · x-ai/grok-4.7Summaries by Vani AI

The captured page is a cookie notice, so only the title's claim that it runs on a 32GB Mac is available.

MarkTechPost's title presents Thinking Machines Inkling 2 Mini as a 26B looped mixture-of-experts model that runs on a 32GB Mac. The fetched page text is a cookie-consent banner and does not include architecture, weights, license, or benchmark details.

Unconfirmed: Details beyond the title are unavailable because the captured page is a cookie notice.

Key facts
  • The title describes Inkling 2 Mini as a 26B looped MoE.
  • It claims the model runs on a 32GB Mac.
  • No release date, license, or evaluation numbers appear in the captured text.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

14 min read at marktechpost.com

Thinking Machines released Inkling 2 Mini, a 26. 4B-parameter looped MoE transformer with 3. 4B active parameters.

MarkTechPost

By Asif Razzaq · marktechpost.com

Read the full article at MarkTechPost

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.