GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
qwen3-coder:30b-a3b-q8_0
OLLAMA GGUFqwen3moe · 30.5B · Q8_0
Jun 18, 2026 · AMD Ryzen 5 5500U
Global Score
79 vs 78
Hardware Fit
59 vs 54
Quality Score
88 vs 88
Hardware
GPT-20B:20b qwen3-coder:30b-a3…
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-20B:20b qwen3-coder:30b-a3…
Tokens/sec19.38.0
First chunk2004 ms1468 ms
TTFT10.4 s1.5 s
Load time10.4 s114.5 s
Memory usage12.9 GB33.5 GB
Memory %20%53%
HW Fit Score Breakdown
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
qwen3-coder:30b-a3b-q8_0
Speed
11/50
TTFT
19/20
Memory
24/30
Quality
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
qwen3-coder:30b-a3b-q8_0
Reasoning
17/20
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: Adequate 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