llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
nemotron-3-nano:4b
OLLAMA GGUFnemotron_h · 4.0B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
74 vs 84
Hardware Fit
99 vs 99
Quality Score
63 vs 78
Hardware
llama3.2:3b nemotron-3-nano:4b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMicrosoft WSL
CPUCortex-A78AEAMD Ryzen 5 5500
Cores612
RAM7 GB8 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSUbuntu 22.04.5 LTSUbuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
llama3.2:3b nemotron-3-nano:4b
Tokens/sec21.1109.2
First chunk1032 ms349 ms
TTFT1.0 s349 ms
Load time8.4 s7.8 s
Memory usage2.4 GB2.6 GB
Memory %32%34%
HW Fit Score Breakdown
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
nemotron-3-nano:4b
Speed
50/50
TTFT
20/20
Memory
29/30
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
nemotron-3-nano:4b
Reasoning
16/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate 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