Inkling-Small is a compact open-source language model published by Thinking Machines on Hugging Face. It supports advanced prompting techniques including reasoning effort levels, system messages, and tool/function calling. The model is designed for efficient inference while maintaining strong performance on reasoning and instruction-following tasks.
Inkling Small sits in PulseGate's Foundation models & chat category. Developers needing smaller, efficient open-weight language models for local or specialized inference tasks. Inkling Small is an open-source project aimed at developers and AI researchers. The project is open source (Apache-2.0). Inkling Small is available on the web, the command line, and API.
Behind Inkling Small is Thinking Machines, and it first shipped in 2025. The project is developed in the open on GitHub with 4k stars and 71 commits in the last 90 days. Among its 3 catalogued features are Language Model, Reasoning Effort Control, and Tool Use Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do