phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Mar 2, 2026 · Apple M4
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
75 vs 79
Hardware Fit
79 vs 59
Quality Score
73 vs 88
Hardware
phi4:14b GPT-20B:20b
MachineMacBook AirGMKtec NucBox EVO-T2S
CPUApple M4Intel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M4Intel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi4:14b GPT-20B:20b
Tokens/sec11.019.3
First chunkN/A2004 ms
TTFT532 ms10.4 s
Load time0.7 s10.4 s
Memory usage13.4 GB12.9 GB
Memory %42%20%
HW Fit Score Breakdown
phi4:14b
Speed
19/50
TTFT
30/20
Memory
30/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
phi4:14b
Reasoning
15/20
Coding
18/20
Instruction
10/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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