# MarkTechPost — Meet Thinking Machines Inkling 2 Mini: 26B Looped MoE Runs on a 32GB Mac

- Company: MarkTechPost (marktechpost.com)
- Announced: 2026-11-21T12:13:50+00:00
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.marktechpost.com/2026/11/21/thinking-machines-inkling-2-mini-looped-transformer/
- Record: https://forck.live/items/39579-meet-thinking-machines-inkling-2-mini-26b-looped-moe-runs-on-a-32gb-mac
- Subject: Reporting

Thinking Machines Lab has released Inkling 2 Mini , an open-weight looped transformer with 26.4B total parameters. The model reuses its middle layers 3 times per token instead of adding more weights. That keeps the checkpoint near 20GB, small enough for a 32GB Mac or 1 NVIDIA DGX Spark. For developers, Inkling 2 Mini is a local option for agentic coding, tool use and document work. It ships under Apache 2.0 on Hugging Face , with hosted inference and fine-tuning on Tinker . TL;DR Size: 26.4B total, 3.4B active (5.4B effective per token with looping), up to 1M-token context. Runs on: Apple silicon with 32GB+ memory, 1 NVIDIA DGX Spark, or GPUs with 32GB+ VRAM. GGUF builds via Unsloth and llama.cpp. Performance: 20.1 on the Artificial Analysis Index, tied with Qwen3.8-27B (self-reported). Best: 79.2% on SWE-bench Verified (bash only). Worst: 15.2% on HLE-Diamond and 50.0% on MultiChallenge. Bottom line: Best: strong agentic coding from a 20GB checkpoint. Worst: weaker knowledge recall and multi-turn instruction following. What is Inkling 2 Mini? Inkling 2 Mini is a sparse Mixture-of-Experts model from Thinking Machines that loops its middle layers. …

---

Record: https://forck.live/items/39579-meet-thinking-machines-inkling-2-mini-26b-looped-moe-runs-on-a-32gb-mac
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
