BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Phi-4 14B

By Microsoft · United States

chat general reasoning
Parameters
14B
License
MIT
Context
16k
VRAM (Q4)
9 GB
Released
December 2024

Overview

Microsoft's Phi-4 14B, trained on ultra-curated synthetic data with a heavy STEM bias. The 14B reasoning leader at the end of 2024.

When to pick this model

  • Math, science, and structured reasoning workloads
  • Coding assistants where quality beats context length
  • MIT-licensed commercial deployments
  • Mid-size GPU deployments needing strong reasoning
  • Replacing larger models on STEM-heavy benchmarks

VRAM requirements by quantization

QuantizationVRAM required
Q4_K_M (recommended)9 GB
Q5_K_M11 GB
Q8_016 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.

Published benchmark scores

BenchmarkScore
MMLU84.8
MATH80.4
HumanEval82.6

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

  • Top-tier 14B reasoning at release
  • MIT license
  • Strong math, science, and code performance
  • Tight, well-formatted outputs

Limitations

  • 16k context is a significant limitation
  • Weaker multilingual coverage than Qwen
  • Narrower world knowledge from synthetic training

Architecture & training

Architecture: Dense · 14B · Phi-4 · Microsoft-exclusive synthetic data

Training: Ultra-filtered Microsoft synthetic corpus. Focus on reasoning and math.

Verdict

The reasoning-focused 14B to pick — just budget around its short context window.

Quick start

ollama run phi4:14b

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

Tools

Is Phi-4 14B the right pick for you?

Compute self-hosted ROI → Back to catalog