Local LLM model page

Phi-4 Mini Reasoning (3.8B)

Phi-4 mini balanced reasoning variant. Good chain-of-thought at tiny size. 62K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
3.8B
Minimum RAM
6 GB
Model size
2.3 GB
Quantization
Q5_K_M

Can Phi-4 Mini Reasoning (3.8B) run locally?

Phi-4 Mini Reasoning (3.8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 6 GB RAM.

Search term for LM Studio or compatible runtimes: phi-4-mini-reasoning

Hugging Face repository: microsoft/Phi-4-mini-reasoning-GGUF

reasoninglightspeed

Strengths

  • Phi-4 mini balanced reasoning variant. Good chain-of-thought at tiny size. 62K downloads.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • reasoning
  • light
  • speed

Benchmarks

Speed: 9/10

Quality: 6/10

Coding: 6/10

Reasoning: 7/10

Technical details

Developer: phi

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-04