Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

gemma3:270m

OLLAMA GGUF

gemma3 · 268.10M · Q8_0

Marginal

Mar 5, 2026 · Apple M3 Pro

Global Score
62 vs 50
Hardware Fit
99 vs 97
Quality Score
46 vs 30

Hardware

microsoft/phi-4-mi… gemma3:270m
MachineMacBook AirMacBook Pro
CPUApple M4Apple M3 Pro
Cores1012
RAM32 GB36 GB
GPUApple M4Apple M3 Pro
OSmacOS 26.3macOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced

Performance

microsoft/phi-4-mi… gemma3:270m
Tokens/sec40.3239.2
First chunk289 ms127 ms
TTFT289 ms127 ms
Load timeN/A0.7 s
Memory usage2.0 GB0.6 GB
Memory %6%2%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

Speed
50/50
TTFT
20/20
Memory
29/30

gemma3:270m

Speed
50/50
TTFT
20/20
Memory
27/30

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

gemma3:270m

Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

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