microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 5, 2026 · Apple M4 Pro
gemma-3-270m-it-qat-mlx
LM-STUDIO MLXgemma3_text · 270M · 4bit
Mar 4, 2026 · Apple M4
Global Score
64 vs 43
Hardware Fit
100 vs 99
Quality Score
48 vs 19
Hardware
microsoft/phi-4-mi… gemma-3-270m-it-qa…
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
microsoft/phi-4-mi… gemma-3-270m-it-qa…
Tokens/sec90.3344.2
First chunk198 ms173 ms
TTFT198 ms173 ms
Load timeN/AN/A
Memory usage2.0 GB0.3 GB
Memory %3%1%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
30/30
gemma-3-270m-it-qat-mlx
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
microsoft/phi-4-mini-re…
Reasoning
7/20
Coding
7/20
Instruction
7/20
Structured
7/15
Math
13/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
gemma-3-270m-it-qat-mlx
Reasoning
4/20
Coding
0/20
Instruction
9/20
Structured
3/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest