llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
76 vs 87
Hardware Fit
100 vs 81
Quality Score
65 vs 90
Hardware
llama3.2:latest GPT-20B:20b
MachineMicro-Star International Co., Ltd. MS-7B79HP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUAMD Ryzen 5 2600X Six-Core ProcessorAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1232
RAM16 GB31 GB
GPUNVIDIA GeForce GTX 1080AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
llama3.2:latest GPT-20B:20b
Tokens/sec57.036.9
First chunk264 ms902 ms
TTFT264 ms4.2 s
Load time9.7 s19.5 s
Memory usage2.6 GB13.1 GB
Memory %16%42%
HW Fit Score Breakdown
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
47/50
TTFT
7/20
Memory
27/30
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-20B:20b
Reasoning
19/20
Coding
17/20
Instruction
14/20
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