gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
81 vs 66
Hardware Fit
100 vs 14
Quality Score
73 vs 88
Hardware
gemma3n:latest GPT-120B:120b
MachineSupermicro AS -2015HS-TNRHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUAMD EPYC 9654P 96-Core ProcessorIntel Core™ i7-14700F
Cores6428
RAM128 GB64 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]NVIDIA GeForce RTX 5080
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
gemma3n:latest GPT-120B:120b
Tokens/sec108.710.1
First chunk333 ms6562 ms
TTFT333 ms10.3 s
Load time4.5 s49.8 s
Memory usage8.6 GB61.5 GB
Memory %7%96%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
GPT-120B:120b
Speed
10/50
TTFT
2/20
Memory
2/30
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
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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