Skip to main content
Local LLM Guide

Model

Phi-4 Reasoning

Start with a supported compressed build and short context. 32GB RAM estimate. Best use: Harder reasoning, math, science, coding puzzles, and users with enough memory for 14B models locally.

14BReasoning

Best use

Harder reasoning, math, science, coding puzzles, and users with enough memory for 14B models locally.

Memory planning

32GB RAM estimate

Expected pace

Depends on your hardware, app, and conversation length

License

MIT; read the model’s terms before use

Who should use this model?

  • Harder reasoning, math, science, coding puzzles, and users with enough memory for 14B models locally.

Choose something else when

  • Avoid on low-RAM laptops, quick chats, or tasks needing short, direct answers without thinking overhead.

What hardware makes sense?

The download is only part of the memory needed. Leave room for the app, the input it processes, and other open programs. For chat models, context includes the instructions, conversation, and answer. Longer context needs more memory.

CPU only
Memory or response time may limit use. Try a smaller model first.
8GB system memory
Use a smaller model for this memory limit.
16GB system memory
Memory or response time may limit use. Try a smaller model first.
32GB system memory
A possible starting point with a compressed model and short conversation; check the exact file size.
8GB GPU memory
Use a smaller model for this memory limit.
12GB GPU memory
Use a smaller model for this memory limit.
24GB GPU memory
Memory or response time may limit use. Try a smaller model first.
Apple unified memory
Memory or response time may limit use. Try a smaller model first.

Model facts that change the decision

Parameters
14B
Input
Text
Published context limit
32,000 tokens
Model format
safetensors · GGUF · Ollama
Suggested compression
Q4_K_M for first local attempts unless a cited runtime recommends a different default.
Typical Q4 file
9.05GB before runtime and context overhead
Languages
Unknown

First setup

Ollama

ollama run phi4-reasoning

LM Studio: Check that your installed app supports the exact model format and task before downloading it.

llama.cpp

Use the cited GGUF repository (bartowski/microsoft_Phi-4-reasoning-GGUF) with current llama.cpp-compatible tooling.

Conditions that change the answer

  • This is not the same as base Phi-4 14B. It is heavier than the mini models and may produce long reasoning-style answers. For llama.cpp-style runtimes, verify the correct reasoning chat template and Jinja handling before following runtime-specific instructions.
  • Commercial use: Permitted under MIT license; verify application-specific obligations before commercial deployment.
  • Phi-4 Reasoning is a larger 14B specialty model for difficult math, science, coding, and planning prompts. It is much heavier than mini models, but useful when reasoning quality matters more than speed or memory savings.

Read the controlling license text →