Thinking Machines Lab releases Inkling 2 Mini (A3B/26B) with support in transformers, llama.cpp and MLX
Original title: 🔥 Thinking Machines Lab dropped Inkling 2 Mini (A3B/26B), amazing size for your local setup
Thinking Machines Lab released Inkling 2 Mini, a 26B-parameter model with 3B active parameters (A3B/26B), sized for local setups. Hugging Face says it vibe-tested the model as a coding companion and shipped support in transformers, llama.cpp and MLX, with a blog post linked.
Why it matters
The post notes support across multiple inference frameworks with a blog link, useful for those considering local deployment of this small model.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.