qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · AMD Ryzen 5 5500U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
82 vs 87
Hardware Fit
71 vs 81
Quality Score
87 vs 90
Hardware
qwen3-coder:30b GPT-20B:20b
MachineHP HP Pavilion Laptop 15-eh1xxxHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUAMD Ryzen 5 5500UAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1232
RAM63 GB31 GB
GPUAMD Radeon(TM) GraphicsAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3-coder:30b GPT-20B:20b
Tokens/sec14.336.9
First chunk869 ms902 ms
TTFT869 ms4.2 s
Load time0.3 s19.5 s
Memory usage20.5 GB13.1 GB
Memory %32%42%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
22/50
TTFT
20/20
Memory
29/30
GPT-20B:20b
Speed
47/50
TTFT
7/20
Memory
27/30
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-20B:20b
Reasoning
19/20
Coding
17/20
Instruction
14/20
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