Latest ContentInference Cookbook Model Library

Phi 4 Reasoning

Phi-4-reasoning is a dense transformer model optimized for structured chain-of-thought reasoning across math, science, and coding tasks. It is fine-tuned from Phi-4 using high-quality reasoning traces to improve step-by-step problem solving. The model features 14B parameters with 40 layers, 5,120 hidden size, and 40 attention heads with 10 key-value heads. It supports a 32K token context window and is trained on curated synthetic and filtered data, delivering strong reasoning performance with efficient inference.

Type	Dense LLM
Capabilities	Text Generation, Instruction Following, Reasoning, Mathematical Reasoning+2 more
Group Release Date	December 11, 2024
Links	Paper\|Blog\|HF Model Card
License	MIT

Inference Instructions

Deploy and run this model on NVIDIA B200 GPUs using the command below. Copy the command to get started with inference.

CONSOLE

docker run -it --rm 
 --runtime=nvidia 
 --gpus all 
 --ipc=host 
 --shm-size=128g 
 -p 8000:8000 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 vllm/vllm-openai:v0.18.1 
 microsoft/Phi-4-reasoning 
  --tensor-parallel-size 2 
 --max-model-len auto 
 --gpu-memory-utilization 0.95 
 --max-num-batched-tokens 65536 
 --max-num-seqs 1024 
 --trust-remote-code