gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
81 vs 74
Hardware Fit
100 vs 99
Quality Score
73 vs 63
Hardware
gemma3n:latest llama3.2:3b
MachineSupermicro AS -2015HS-TNRNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD EPYC 9654P 96-Core ProcessorCortex-A78AE
Cores646
RAM128 GB7 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Integrated / Unknown
OSUbuntu 24.04.3 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest llama3.2:3b
Tokens/sec108.721.1
First chunk333 ms1032 ms
TTFT333 ms1.0 s
Load time4.5 s8.4 s
Memory usage8.6 GB2.4 GB
Memory %7%32%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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