phi
3.8B parameters
Commercial OK

Phi-4 Reasoning Mini 4B

Phi-4 reasoning at the edge tier. 3.8B with reasoning-token emission. The right pick when reasoning matters AND edge deployment is required.

License: MIT·Released Apr 8, 2026·Context: 131,072 tokens

Overview

Phi-4 reasoning at the edge tier. 3.8B with reasoning-token emission. The right pick when reasoning matters AND edge deployment is required.

Family & lineage

How this model relates to others in its lineage. Family members share architecture and training-data roots; parent / children edges record direct distillation or fine-tune relationships.

Parent / base model
Phi-4 Reasoning 14B14B

Strengths

  • Reasoning at edge tier
  • MIT license

Weaknesses

  • 3.8B ceiling on reasoning depth

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M2.4 GB4 GB

Get the model

HuggingFace

Original weights

huggingface.co/microsoft/Phi-4-reasoning-mini-4B

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Phi-4 Reasoning Mini 4B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step down
Smaller — faster, runs on weaker hardware

Frequently asked

What's the minimum VRAM to run Phi-4 Reasoning Mini 4B?

4GB of VRAM is enough to run Phi-4 Reasoning Mini 4B at the Q4_K_M quantization (file size 2.4 GB). Higher-quality quantizations need more.

Can I use Phi-4 Reasoning Mini 4B commercially?

Yes — Phi-4 Reasoning Mini 4B ships under the MIT, which permits commercial use. Always read the license text before deployment.

What's the context length of Phi-4 Reasoning Mini 4B?

Phi-4 Reasoning Mini 4B supports a context window of 131,072 tokens (about 131K).

Source: huggingface.co/microsoft/Phi-4-reasoning-mini-4B

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.