Skip to content
Source: Thinking Machines Lab

🧠Inkling 2 Mini Runs 26.4B Parameters on a Laptop, Beats Open Rivals on Agentic Coding

Your laptop can now run a model that beats bigger open rivals

TL;DR

Inkling 2 Mini ships with open weights and a ~20GB footprint, so it runs on consumer laptops. It leads open models under 100B parameters on DeepSWE v1.1 (48.2%) and Vals Index v2.2 (46.5%). If you do agentic coding locally, this is the one to test this week.

Inkling 2 Mini just dropped with open weights, and it is the strongest open model under 100B total parameters on several agentic benchmarks. The trick is architecture: it's a looped transformer that runs its middle layers three times per token, which buys reasoning depth without bloating the parameter count. If you're building coding agents or search-heavy tools, this matters more than another chat model. It scores ahead of every comparable model on DeepSWE v1.1 and SWE-bench Pro v2, and it leads on BrowseComp, DeepSearchQA, and MCP Atlas. It gets there by leaning on search and tools rather than memorized facts, so don't expect it to be a trivia machine. The numbers: 26.4B total parameters, 3.4B active per token, roughly 20GB total memory, and a theoretical decode ceiling of 614 GB/s with BF16 weights at batch size one. It's available on Tinker today for inference and customization. The catch is that factuality on AA-Omniscience is only in line with peers, so pair it with retrieval.

Inkling 2 Mini Runs 26.4B Parameters on a Laptop, Beats Open Rivals on Agentic Coding — Thinking Machines Lab

Key Points

1

Inkling 2 Mini scores 48.2% on DeepSWE v1.1 and 46.5% on Vals Index v2.2, leading every open-weights model under 100B total parameters on those benchmarks.

Keep reading — it's free

Enter your email to keep reading — plus the best of AI & tech, daily. Free, forever.

Also get
or

Already a member? Sign in

open-weightslooped-transformeragentic-codinglocal-inferencebenchmarks

Comments

Subscribe to join the conversation...

Be the first to comment