Phi-4 Reasoning 14B

Overview

Microsoft's 14B reasoner that beats R1-Distill-Llama-70B on AIME and GPQA with 50x fewer parameters. MIT-licensed, English-first, with a 32K context.

When to pick this model

• You want frontier-class reasoning that fits on a 16GB or 24GB GPU
• You need MIT licensing for commercial deployment
• You're solving math, science, or logic problems in English
• You want to replace a 70B reasoner with something far cheaper to run

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	9 GB
Q5_K_M	11 GB
Q8_0	16 GB
FP16 (no quantization)	28 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• Beats R1-Distill-Llama-70B on AIME and GPQA with 50x fewer parameters
• MIT license
• Increased RoPE base frequency improves long-form reasoning
• Practical hardware footprint for a frontier-class reasoner

Limitations

• English-first — weak multilingual performance
• Weaker on non-Python code generation
• 32K context vs 128K on most peers

Architecture & training

Architecture: Dense · SFT on o3-mini traces · Plus variant adds RL

Training: RoPE base freq. increased vs Phi-4 base.

Quick start

ollama run phi4-reasoning:14b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.