Phi-4 Mini
PhiMITtext

Phi-4 Mini

Updated Jun 7, 2026
Parameters
3B
Context
16,384
License
MIT
Updated
Jun 7, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

8.4

AA Index

Coding

3.6

AA Index

Agentic

2.7

AA Index

Math

6.7

AA Index

Intelligence Index - Phi-4 Mini vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 4.8 (max)
61.4
closed
GPT-5.5 (xhigh)
60.2
closed
Claude Opus 4.7 (max)
57.3
closed
Gemini 3.1 Pro Preview
57.2
closed
Qwen3.7 Max
56.6
closed
Kimi K2.6
53.9
open
MiMo-V2.5-Pro
53.8
open
Phi-4 Mini
8.4
open

Coding Index comparison

GPT-5.5 (xhigh)
59.1
closed
Claude Opus 4.8 (max)
56.7
closed
Gemini 3.1 Pro Preview
55.5
closed
Claude Opus 4.7 (Non-reasoning, high)
53.1
closed
GPT-5.3 Codex (xhigh)
53.1
closed
DeepSeek V4 Pro (Max)
47.5
open
Kimi K2.6
47.1
open
Phi-4 Mini
3.6
open

Agentic Index comparison

Claude Opus 4.8 (max)
77.8
closed
GPT-5.5 (xhigh)
74.1
closed
Claude Opus 4.7 (max)
71.3
closed
Gemini 3.5 Flash (medium)
70.4
closed
MiniMax-M3
68.6
closed
MiMo-V2.5-Pro
67.4
open
DeepSeek V4 Pro (Max)
67.2
open
Phi-4 Mini
2.7
open

Math Index comparison

Nova 2.0 Lite (high)
94.3
closed
gpt-oss-120b (high)
93.4
open
NVIDIA Nemotron 3 Nano
91
open
K-EXAONE
90.3
open
Nova 2.0 Omni (medium)
89.7
closed
gpt-oss-20B (high)
89.3
open
Nova 2.0 Pro Preview (medium)
89
closed
Phi-4 Mini
6.7
open

Benchmark data from Artificial Analysis · updated 2026-06-07.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
MMLU64
HumanEval65
MT-Bench7.5
GSM8K78
MMLUPRO46.5
GPQA33.1
AIME3

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit Phi-4 Mini with real runtime overhead.
Q4_K_M
2.5 GB
Q5_K_M
3 GB
Q8_0
4.5 GB
FP16
6 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

Ollamaeasiest
ollama run phi-4-mini:3b
vLLMOpenAI-compatible API
vllm serve microsoft/Phi-4-mini-instruct

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

Phi-4 Mini

Phi-4 Mini brings Microsoft's synthetic-data training approach to a 3.8-billion-parameter model. It targets edge deployment with strong coding performance for its size.

Key features

  1. Synthetic data training - inherits Phi-4's approach
  2. 64 MMLU - strong for 3.8B
  3. 65 HumanEval - best-in-class coding for sub-4B
  4. MIT license - fully open

How to run

ollama run phi-4-mini:3b

Frequently asked

Quick answers to common questions

How much VRAM does Phi-4 Mini need?

Phi-4 Mini with 3B parameters needs approximately 2.5 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Phi-4 Mini better than other Phi models?

Phi-4 Mini scores 64 on MMLU and 65 on HumanEval. It has 3B parameters with 16,384 context - a strong choice for edge, mobile, chatbots.

What license is Phi-4 Mini under?

Phi-4 Mini is released under the MIT license, making it suitable for most commercial and personal projects.

What hardware runs Phi-4 Mini well?

With 3B parameters, Phi-4 Mini requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for Phi-4 Mini?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~3 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with Phi-4 Mini?

Phi-4 Mini competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Compare & pair with

Similar models and recommended hardware

Recommended hardware

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.