llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
67 vs 90
Hardware Fit
77 vs 79
Quality Score
63 vs 94
Hardware
llama3.2:3b GPT-20B:20b
MachineLENOVO 20U30029MBHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Core™ i5-10210UAMD Ryzen 9 9955HX3D 16-Core Processor
Cores832
RAM15 GB31 GB
GPUCometLake-U GT2 [UHD Graphics]AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSPop 24.04 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
llama3.2:3b GPT-20B:20b
Tokens/sec10.036.6
First chunk1166 ms722 ms
TTFT1.2 s4.7 s
Load time6.8 s0.3 s
Memory usage3.8 GB13.1 GB
Memory %25%42%
HW Fit Score Breakdown
llama3.2:3b
Speed
27/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
Quality
llama3.2:3b
Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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