llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
76 vs 67
Hardware Fit
100 vs 21
Quality Score
65 vs 87
Hardware
llama3.2:latest GPT-120B:120b
MachineMicro-Star International Co., Ltd. MS-7B79GMKtec NucBox EVO-T2S
CPUAMD Ryzen 5 2600X Six-Core ProcessorIntel Core™ Ultra X7 358H
Cores1216
RAM16 GB64 GB
GPUNVIDIA GeForce GTX 1080Intel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
llama3.2:latest GPT-120B:120b
Tokens/sec57.011.8
First chunk264 ms4674 ms
TTFT264 ms9.3 s
Load time9.7 s77.6 s
Memory usage2.6 GB61.0 GB
Memory %16%96%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
GPT-120B:120b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
14/15
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