qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 5, 2026 · Apple M4 Pro
Global Score
58 vs 64
Hardware Fit
82 vs 100
Quality Score
48 vs 48
Hardware
qwen3:14b microsoft/phi-4-mi…
MachineMacBook ProMac mini
CPUApple M1 MaxApple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M1 MaxApple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3:14b microsoft/phi-4-mi…
Tokens/sec24.490.3
First chunk294 ms198 ms
TTFT7.9 s198 ms
Load time3.7 sN/A
Memory usage13.8 GB2.0 GB
Memory %43%3%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3:14b
Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
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
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