Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Excellent

Jul 7, 2026 · Cortex-X925

Global Score
81 vs 83
Hardware Fit
100 vs 60
Quality Score
73 vs 93

Hardware

gemma3n:latest gemma4:31b
MachineSupermicro AS -2015HS-TNRASUSTeK COMPUTER INC. GX10
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 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance

Performance

gemma3n:latest gemma4:31b
Tokens/sec108.710.9
First chunk333 ms681 ms
TTFT333 ms681 ms
Load time4.5 s16.6 s
Memory usage8.6 GB21.4 GB
Memory %7%18%

HW Fit Score Breakdown

gemma3n:latest

Speed
50/50
TTFT
20/20
Memory
30/30

gemma4:31b

Speed
10/50
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

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest