microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
Global Score
62 vs 90
Hardware Fit
99 vs 85
Quality Score
46 vs 92
Hardware
microsoft/phi-4-mi… unsloth/gemma-4-26…
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
microsoft/phi-4-mi… unsloth/gemma-4-26…
Tokens/sec40.324.9
First chunk289 ms15 ms
TTFT289 ms817 ms
Load timeN/AN/A
Memory usage2.0 GB16.8 GB
Memory %6%70%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
unsloth/gemma-4-26b-a4b…
Speed
50/50
TTFT
20/20
Memory
15/30
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
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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