qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
58 vs 67
Hardware Fit
82 vs 21
Quality Score
48 vs 87
Hardware
qwen3:14b GPT-OSS-120B:120B
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M1 MaxIntel Core™ Ultra X7 358H
Cores1016
RAM32 GB64 GB
GPUApple M1 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3:14b GPT-OSS-120B:120B
Tokens/sec24.411.7
First chunk294 ms4289 ms
TTFT7.9 s9.2 s
Load time3.7 s84.1 s
Memory usage13.8 GB61.0 GB
Memory %43%96%
HW Fit Score Breakdown
qwen3:14b
Speed
47/50
TTFT
5/20
Memory
30/30
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
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
GPT-OSS-120B:120B
Reasoning
18/20
Coding
19/20
Instruction
10/20
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