Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
81 vs 62
Hardware Fit
100 vs 77
Quality Score
73 vs 55

Hardware

gemma3n:latest google/gemma-4-e4b
MachineSupermicro AS -2015HS-TNRLENOVO 82JQ
CPUAMD EPYC 9654P 96-Core ProcessorAMD Ryzen 7 5800H
Cores6416
RAM128 GB16 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 家庭版 中文版 10.0.26100
Archx64x64
Power Modeperformancebalanced

Performance

gemma3n:latest google/gemma-4-e4b
Tokens/sec108.727.6
First chunk333 ms23 ms
TTFT333 ms480 ms
Load time4.5 sN/A
Memory usage8.6 GB13.2 GB
Memory %7%83%

HW Fit Score Breakdown

gemma3n:latest

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

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

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

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View gemma3n:latest details | View google/gemma-4-e4b details

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