GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Mar 5, 2026 · AMD Ryzen 9 8945HS
Global Score
79 vs 62
Hardware Fit
47 vs 91
Quality Score
93 vs 50
Hardware
GPT-120B:120b llama3.2:1b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV
CPUIntel Core™ i7-14700FAMD Ryzen 9 8945HS
Cores2816
RAM128 GB15 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b llama3.2:1b
Tokens/sec18.2170.2
First chunk1719 ms142 ms
TTFT3.9 s142 ms
Load time50.9 s3.2 s
Memory usage61.5 GB1.6 GB
Memory %48%11%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
21/30
Quality
GPT-120B:120b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.2:1b
Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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