microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

smollm2-360m-instruct

LM-STUDIO MLX

llama · 360M · bf16

Marginal

Mar 4, 2026 · Apple M4

Global Score

62 vs 52

Hardware Fit

99 vs 100

Quality Score

46 vs 32

Hardware

microsoft/phi-4-mi… smollm2-360m-instr…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… smollm2-360m-instr…

Tokens/sec40.3121.1

First chunk289 ms106 ms

TTFT289 ms106 ms

Load timeN/AN/A

Memory usage2.0 GB0.7 GB

Memory %6%2%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed

50/50

TTFT

20/20

Memory

29/30

smollm2-360m-instruct

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

microsoft/phi-4-mini-re…

Reasoning

7/20

Coding

6/20

Instruction

7/20

Structured

7/15

Math

12/15

Multilingual

7/10

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

smollm2-360m-instruct

Reasoning

4/20

Coding

3/20

Instruction

12/20

Structured

7/15

Math

2/15

Multilingual

4/10

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

View microsoft/phi-4-mi… details | View smollm2-360m-instr… details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest