26.4B model 'Inkling 2 Mini' with vision, tool use and reasoning spotted in GGUF

vboykis · x · 2026-11-21

A screenshot shared by vboykis shows a download page for a new model, Inkling 2 Mini: 26.4B params, a custom inkling2loop architecture, and capability tags for Vision, Tool Use, and Reasoning.

It's offered as GGUF (Q4KM, 18.12 GB) with full GPU offload possible, making it runnable locally.

Related event: Thinking Machines Releases Inkling 2 Mini; Unsloth Ships GGUF for Local Use(4 posts)→

Original post →

More from Models

Models channel →