Inkling-NVFP4 is a language model hosted on Hugging Face that features an advanced Jinja-based chat template with support for system, user, assistant, and tool messages. It includes programmable reasoning effort levels and structured function calling capabilities. The model is intended for developers building applications that require controllable inference behavior.
Inkling is a Foundation models & chat project. It focuses on enabling controllable reasoning and structured tool use in language model inference. Inkling is an open-source project aimed at developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
Thinking Machines builds and maintains Inkling, and it first shipped in 2025. Development happens publicly on GitHub with 3.9k stars and 69 commits in the last 90 days. Among its 3 catalogued features are custom chat template, reasoning effort control, and tool calling 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