gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
81 vs 63
Hardware Fit
100 vs 62
Quality Score
73 vs 63
Hardware
gemma3n:latest gemma4:12b
MachineSupermicro AS -2015HS-TNRMacBook Pro
CPUAMD EPYC 9654P 96-Core ProcessorApple M1 Pro
Cores6410
RAM128 GB16 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M1 Pro
OSUbuntu 24.04.3 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest gemma4:12b
Tokens/sec108.715.3
First chunk333 ms1142 ms
TTFT333 ms30.0 s
Load time4.5 s5.4 s
Memory usage8.6 GB7.6 GB
Memory %7%47%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b
Speed
36/50
TTFT
0/20
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
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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