AI News Daily한국어
Saturday, November 21, 2026

Story 3 of 7

A 26B model that loops its middle 12 layers three times: Thinking Machines' Inkling 2 Mini runs on a laptop

First seen on X 7 hours ago@thinkymachines ♥ 4,2257 views

A 26B model that loops its middle 12 layers three times: Thinking Machines' Inkling 2 Mini runs on a laptopA 26B model that loops its middle 12 layers three times: Thinking Machines' Inkling 2 Mini runs on a laptopA 26B model that loops its middle 12 layers three times: Thinking Machines' Inkling 2 Mini runs on a laptopA 26B model that loops its middle 12 layers three times: Thinking Machines' Inkling 2 Mini runs on a laptop

Mira Murati's Thinking Machines Lab released Inkling 2 Mini, an open-weights model small enough to run on a laptop.

"Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you," the company posted on Nov. 20, drawing 4,300 likes. Inkling 2 Mini is a looped transformer: of its 24 layers, the middle 12 run three times per token while the first and last six run once, so the model reasons more while writing less. It has 26.4B total parameters with 5.4B active per token once looping is counted, was trained and ships natively in NVFP4 at around 20GB, and is licensed Apache 2.0.

You can try it now. Weights are on Hugging Face, Ollama supports it in the 0.40.17 pre-release on Macs with 32GB or more, and Unsloth published GGUF files it says run in 16GB of RAM. It also runs on Nvidia's DGX Spark and is available on Thinking Machines' Tinker for inference and fine-tuning.

The company says the model leads every open model under 100B parameters on DeepSWE v1.1 (48.2%) and Vals Index v2.2 (46.5%). Artificial Analysis scores it 20 on its Intelligence Index, tied with Qwen3.8-27B, at $0.59 and 9.0 minutes per task versus $3.53 and 38.2 minutes for Qwen. GPT-6 Luna, though, scores 28 for $0.15 per task, and Thinking Machines says Mini trails Qwen on multi-turn chat and heavily constrained instructions.

Looping also raises a safety question, since a model can think longer without writing its reasoning down. Thinking Machines says the chain of thought stayed legible at this scale but "this may not stay the case," and released a variable-loop research model; Goodfire got early access to study its internals.

Comments 0

Select a sentence in the story (long-press on phones) to comment on it.

“Some of you thought that Inkling 2 Small was too big at 594B parameters.”

Next story →Cursor told Congress it may phase out Chinese AI models; Musk replies "we aren't serving open source models"Read an AI Insight →The generation that starts as team leads: KAIST's Prof. Minhyuk Sung says "'GPT did it' is no excuse"

Get tomorrow's stories as an alert

We'll ping you when each new edition or breaking story lands. Free, no sign-up.

Daily morning AI news, new AI Insights, and a monthly briefing of top stories on the 1st.

AdPut your product here. About 5,000 people a month read AI news on this site.Advertise with us ›

More stories from the same day

  1. AI's Riemann hypothesis proof independently checked within a day: "the chance that anything is fishy is approximately zero"
  2. "Nvidia did everything right," yet the Nasdaq plunges 5.28% and wipes out its 2026 gains
  3. Cursor told Congress it may phase out Chinese AI models; Musk replies "we aren't serving open source models"
  4. ChatGPT's redesigned app gives dots their own tab; hours later Claude's app changed too
  5. He gave Claude the keys to the sheep pen, and now it counts the flock in every night
  6. An AI animation gets 33,000 likes' worth of scorn for copying Arcane, while an AI movie's poster was painted by humans
See all of Saturday, November 21, 2026 →

* Summaries and publishing on this page are done by an automated agent. Check the facts against the original links.

Privacy PolicySupportSend feedbackAdvertiseDiscord botClaude Code & CodexRSSListed on Sell With boost