Back to leaderboard

microsoft/phi-4-mini-reasoning

LM-STUDIO MLX

phi3 · 3.8B · 4bit

Good

Mar 3, 2026 · Apple M4

gemma2:9b

OLLAMA GGUF

gemma2 · 9.2B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
62 vs 76
Hardware Fit
99 vs 89
Quality Score
46 vs 71

Hardware

microsoft/phi-4-mi… gemma2:9b
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… gemma2:9b
Tokens/sec40.317.5
First chunk289 msN/A
TTFT289 ms347 ms
Load timeN/A0.8 s
Memory usage2.0 GB8.2 GB
Memory %6%26%

HW Fit Score Breakdown

microsoft/phi-4-mini-re…

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

gemma2:9b

Speed
29/50
TTFT
30/20
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

gemma2:9b

Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

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