qwen2.5:3b
OLLAMA GGUFqwen2 · 3.1B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
77 vs 79
Hardware Fit
100 vs 59
Quality Score
67 vs 88
Hardware
qwen2.5:3b GPT-20B:20b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperGMKtec NucBox EVO-T2S
CPUCortex-A78AEIntel Core™ Ultra X7 358H
Cores616
RAM7 GB64 GB
GPUIntegrated / UnknownIntel(R) Arc(TM) B390 GPU
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen2.5:3b GPT-20B:20b
Tokens/sec21.419.3
First chunk1006 ms2004 ms
TTFT1.0 s10.4 s
Load time6.4 s10.4 s
Memory usage2.0 GB12.9 GB
Memory %27%20%
HW Fit Score Breakdown
qwen2.5:3b
Speed
50/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
26/50
TTFT
3/20
Memory
30/30
Quality
qwen2.5:3b
Reasoning
12/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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