microsoft/phi-4-mini-reasoning

phi3 · 3.8B · 4bit

MacBook Air (Apple M4)

32 GB · macOS 26.3

Tested on March 3, 2026 · Submitted by Topaz750

Top 62% Compare

Global Score

62 /100

Good

Hardware Fit

99/100

Quality

46/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: MacBook Air
CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 40.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 289 ms
Time to first token How fast the model starts responding — lower is better: 289 ms
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 2.0 GB (6%)
Total tokens Total number of tokens generated across all benchmark prompts: 1463

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

29/30

Quality

Reasoning

7/20

Coding

6/20

Instruction following

7/20

Structured output

7/15

Math

12/15

Multilingual

7/10

Category levels

Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate

Metadata

Spec version: 0.2.0
Runtime: LM Studio 0.4.6+1
Model format: MLX
Hardware profile: BALANCED
Result hash: 4e7f5a862ee15807696acc8e06c3fdc6939678de693f483341ab8dad8348b006

Interpretation

Hardware fit: 99/100. Overall suitability: GOOD (Global 62/100). Category profile: Reasoning: Weak, Coding: Weak, Instruction Following: Weak, Structured Output: Weak, Math: Strong, Multilingual: Adequate.

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest