qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · AMD Ryzen 5 5500U
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
82 vs 67
Hardware Fit
71 vs 21
Quality Score
87 vs 87
Hardware
qwen3-coder:30b GPT-120B:120b
MachineHP HP Pavilion Laptop 15-eh1xxxGMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 5500UIntel Core™ Ultra X7 358H
Cores1216
RAM63 GB64 GB
GPUAMD Radeon(TM) GraphicsIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3-coder:30b GPT-120B:120b
Tokens/sec14.311.8
First chunk869 ms4674 ms
TTFT869 ms9.3 s
Load time0.3 s77.6 s
Memory usage20.5 GB61.0 GB
Memory %32%96%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
22/50
TTFT
20/20
Memory
29/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
qwen3-coder:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
GPT-120B:120b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
14/15
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