Thinking Machines Releases Inkling 2 Mini, an Open-Weights Looped Model for Local Use
Thinking Machines Lab released Inkling 2 Mini on November 20 as an open-weights multimodal model that accepts text and images. The model can run on local hardware such as Apple silicon Macs with at least 32 GB of unified memory and NVIDIA DGX Spark systems. Its design reuses the middle layers three times per token, adding computation without storing extra weights. The company reports benchmark results for coding and tool use, though the article cautions that local performance and safety depend on the user's hardware and setup.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.
Discussion (0)
Log in to join the discussion and vote.
Log in