Back to leaderboard

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
81 vs 85
Hardware Fit
100 vs 64
Quality Score
73 vs 94

Hardware

gemma3n:latest gemma-4-31b-it-mlx
MachineSupermicro AS -2015HS-TNRMacBook Pro
CPUAMD EPYC 9654P 96-Core ProcessorApple M4 Max
Cores6416
RAM128 GB128 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M4 Max
OSUbuntu 24.04.3 LTSmacOS 26.5.2
Archx64arm64
Power Modeperformancebalanced

Performance

gemma3n:latest gemma-4-31b-it-mlx
Tokens/sec108.713.6
First chunk333 ms16 ms
TTFT333 ms558 ms
Load time4.5 s12.3 s
Memory usage8.6 GB0.0 GB
Memory %7%0%

HW Fit Score Breakdown

gemma3n:latest

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

gemma-4-31b-it-mlx

Speed
14/50
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

gemma-4-31b-it-mlx

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma3n:latest details | View gemma-4-31b-it-mlx 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