deepseek-r1:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Mar 2, 2026 · Apple M4
microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
Global Score
22 vs 62
Hardware Fit
50 vs 99
Quality Score
10 vs 46
Hardware
deepseek-r1:14b microsoft/phi-4-mi…
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:14b microsoft/phi-4-mi…
Tokens/sec11.440.3
First chunkN/A289 ms
TTFT30.0 s289 ms
Load time1.0 sN/A
Memory usage16.5 GB2.0 GB
Memory %52%6%
HW Fit Score Breakdown
deepseek-r1:14b
Speed
20/50
TTFT
0/20
Memory
30/30
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
deepseek-r1:14b
Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
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
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