qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
75 vs 90
Hardware Fit
50 vs 79
Quality Score
86 vs 94
Hardware
qwen2.5:72b GPT-20B:20b
MachineNVIDIA NVIDIA_DGX_SparkHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUCortex-X925AMD Ryzen 9 9955HX3D 16-Core Processor
Cores2032
RAM122 GB31 GB
GPUDevice 2e12AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
qwen2.5:72b GPT-20B:20b
Tokens/sec4.436.6
First chunk529 ms722 ms
TTFT529 ms4.7 s
Load time49.7 s0.3 s
Memory usage54.0 GB13.1 GB
Memory %44%42%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
Quality
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
15/15
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