Inkling 2 Mini reasoning model gets a GGUF build for local use

kalyan_kpl · x · 2026-11-23

A GGUF quantized version of the Inkling 2 Mini model is now on Hugging Face (AtomicChat/Inkling-2-Mini-GGUF) for local deployment. Its chat template reveals a tunable reasoningeffort parameter (0–0.99) plus tool declaration support.

Related event: Uncensored GGUF builds of Inkling 2 Mini spread, running locally on 12GB VRAM(5 posts)→

Original post →

More from Models

Models channel →