llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
74 vs 95
Hardware Fit
99 vs 98
Quality Score
63 vs 94
Hardware
llama3.2:3b gpt-oss:20b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperASUS
CPUCortex-A78AEIntel Core™ Ultra 9 285K
Cores624
RAM7 GB47 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b gpt-oss:20b
Tokens/sec21.1239.9
First chunk1032 ms180 ms
TTFT1.0 s616 ms
Load time8.4 s4.3 s
Memory usage2.4 GB13.9 GB
Memory %32%29%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
gpt-oss:20b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
llama3.2:3b
Reasoning
10/20
Coding
14/20
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-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
14/15
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