llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
GPT-OSS-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
74 vs 93
Hardware Fit
99 vs 92
Quality Score
63 vs 93
Hardware
llama3.2:3b GPT-OSS-20B:20b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUCortex-A78AEIntel Core™ i7-14700F
Cores628
RAM7 GB128 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5080
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
llama3.2:3b GPT-OSS-20B:20b
Tokens/sec21.1178.6
First chunk1032 ms695 ms
TTFT1.0 s1.4 s
Load time8.4 s31.2 s
Memory usage2.4 GB11.9 GB
Memory %32%9%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
GPT-OSS-20B:20b
Speed
50/50
TTFT
12/20
Memory
30/30
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:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
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