GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · AMD Ryzen 5 5500U
Global Score
67 vs 82
Hardware Fit
21 vs 71
Quality Score
87 vs 87
Hardware
GPT-OSS-120B:120B qwen3-coder:30b
MachineGMKtec NucBox EVO-T2SHP HP Pavilion Laptop 15-eh1xxx
CPUIntel Core™ Ultra X7 358HAMD Ryzen 5 5500U
Cores1612
RAM64 GB63 GB
GPUIntel(R) Arc(TM) B390 GPUAMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archx64x64
Power Modebalancedbalanced
Performance
GPT-OSS-120B:120B qwen3-coder:30b
Tokens/sec11.714.3
First chunk4289 ms869 ms
TTFT9.2 s869 ms
Load time84.1 s0.3 s
Memory usage61.0 GB20.5 GB
Memory %96%32%
HW Fit Score Breakdown
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
qwen3-coder:30b
Speed
22/50
TTFT
20/20
Memory
29/30
Quality
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
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
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