gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
81 vs 84
Hardware Fit
100 vs 82
Quality Score
73 vs 85
Hardware
gemma3n:latest gemma4:12b-mlx
MachineSupermicro AS -2015HS-TNRMacBook Pro
CPUAMD EPYC 9654P 96-Core ProcessorApple M2 Pro
Cores6410
RAM128 GB16 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M2 Pro
OSUbuntu 24.04.3 LTSmacOS 26.5
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest gemma4:12b-mlx
Tokens/sec108.727.2
First chunk333 ms732 ms
TTFT333 ms8.1 s
Load time4.5 s3.5 s
Memory usage8.6 GB7.1 GB
Memory %7%44%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
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
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
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