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)→
More from Models
- LeCun: Training LLMs on human knowledge yields memory, not intelligence — haider1 · 2026-11-22
- Claude veteran shocked by Gemini's leap, weighs switching to Google AI Ultra — ScreenPlayLife · 2026-11-22
- Gemini Neon builds an interactive USL lock-contention UI exposing a testing blind spot — tianyin_xu · 2026-11-22
- New spatial planning benchmark: GPT-6 and Claude Opus 5.5 fail parking route tasks — songhan_mit · 2026-11-22
- Microsoft's new models reportedly up to 80x cheaper and 50x faster — ChrisUniverse · 2026-11-22
- Inkling 2 Mini uncensored: refusals 100%→0% with a 40MB LoRA, 98% MMLU kept — Top-Eye-8104 · 2026-11-22