Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
76 vs 68
Hardware Fit
46 vs 93
Quality Score
89 vs 57

Hardware

gemma4:31b google/gemma-4-e4b
MachineMacBook ProLENOVO 82JQ
CPUApple M4 MaxAMD Ryzen 7 5800H
Cores1616
RAM64 GB16 GB
GPUApple M4 MaxNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.3.1Microsoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:31b google/gemma-4-e4b
Tokens/sec22.426.2
First chunk565 ms17 ms
TTFT30.0 s572 ms
Load time6.9 sN/A
Memory usage43.9 GB6.5 GB
Memory %69%41%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

Quality

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
View gemma4:31b 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