Model ID
microsoft/Phi-4-reasoning
Capabilities
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.
About this model
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.
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (microsoft/Phi-4-reasoning). Released under MIT. Further reading: Paper · Blog
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
B200
1,440 GB
Engine
vLLM
SGLang
Deployment code
Access Restricted
Enter your email to get access to this content
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on B200 · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
NVIDIA HGX B200
Unlock Next-Generation AI Power on Vultr Cloud GPU