nvidia/Phi-4-reasoning-plus-NVFP4 is an NVIDIA-optimized, quantized version of Microsoft's Phi-4 model. It is designed for systematic, step-by-step reasoning using a <think> and <solution> output format. The model runs locally with support for NVIDIA hardware acceleration and is distributed as open weights on Hugging Face.
Phi 4 Reasoning Plus sits in PulseGate's Foundation models & chat category. It focuses on enabling efficient local inference of a reasoning-focused language model with NVIDIA-specific quantization. It is built as an open-source project for developers and AI researchers. Phi 4 Reasoning Plus is open source under the Apache-2.0 license. It ships for the web and API.
It is developed by NVIDIA (United States), and it first shipped in 2024. The project is developed in the open on GitHub with 3.3k stars and 350 commits in the last 90 days. Key capabilities include Structured Reasoning, Step-by-Step Thinking, and Microsoft Phi Architecture.
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