llama3.2:1b
OLLAMA GGUFllama · 1.2B · Q8_0
Mar 5, 2026 · AMD Ryzen 9 8945HS
GPT-OSS-120B:120B
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ Ultra X7 358H
Global Score
62 vs 67
Hardware Fit
91 vs 21
Quality Score
50 vs 87
Hardware
llama3.2:1b GPT-OSS-120B:120B
MachineASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UVGMKtec NucBox EVO-T2S
CPUAMD Ryzen 9 8945HSIntel Core™ Ultra X7 358H
Cores1616
RAM15 GB64 GB
GPUNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M GraphicsIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
llama3.2:1b GPT-OSS-120B:120B
Tokens/sec170.211.7
First chunk142 ms4289 ms
TTFT142 ms9.2 s
Load time3.2 s84.1 s
Memory usage1.6 GB61.0 GB
Memory %11%96%
HW Fit Score Breakdown
llama3.2:1b
Speed
50/50
TTFT
20/20
Memory
21/30
GPT-OSS-120B:120B
Speed
15/50
TTFT
4/20
Memory
2/30
Quality
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
GPT-OSS-120B:120B
Reasoning
18/20
Coding
19/20
Instruction
10/20
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