gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
81 vs 83
Hardware Fit
100 vs 64
Quality Score
73 vs 91
Hardware
gemma3n:latest gpt-oss:120b
MachineSupermicro AS -2015HS-TNRNVIDIA NVIDIA_DGX_Spark
CPUAMD EPYC 9654P 96-Core ProcessorCortex-X925
Cores6420
RAM128 GB122 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Device 2e12
OSUbuntu 24.04.3 LTSUbuntu 24.04.5 LTS
Archx64arm64
Power Modeperformanceperformance
Performance
gemma3n:latest gpt-oss:120b
Tokens/sec108.728.6
First chunk333 ms422 ms
TTFT333 ms2.5 s
Load time4.5 s9.9 s
Memory usage8.6 GB60.1 GB
Memory %7%49%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
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-oss:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
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