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
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
81 vs 67
Hardware Fit
100 vs 77
Quality Score
73 vs 63
Hardware
gemma3n:latest llama3.2:3b
MachineSupermicro AS -2015HS-TNRLENOVO 20U30029MB
CPUAMD EPYC 9654P 96-Core ProcessorIntel Core™ i5-10210U
Cores648
RAM128 GB15 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]CometLake-U GT2 [UHD Graphics]
OSUbuntu 24.04.3 LTSPop 24.04 LTS
Archx64x64
Power Modeperformancelow-power
Performance
gemma3n:latest llama3.2:3b
Tokens/sec108.710.0
First chunk333 ms1166 ms
TTFT333 ms1.2 s
Load time4.5 s6.8 s
Memory usage8.6 GB3.8 GB
Memory %7%25%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
llama3.2:3b
Speed
27/50
TTFT
20/20
Memory
30/30
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
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
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