microsoft/Phi-4-mini-reasoning

microsoft/Phi-4-mini-reasoning is a 3.8 billion parameter decoder-only Transformer model from the Phi-4 family, optimized for advanced mathematical reasoning. Trained on 150 billion tokens of synthetic math data, it supports a 128K token context length. This model excels at multi-step, logic-intensive mathematical problem-solving, making it suitable for memory/compute constrained environments and latency-bound scenarios.