Back to leaderboard

gemma4:12b-it-qat

OLLAMA GGUF

gemma4 · 11.9B · Q4_0

Excellent

Jun 25, 2026 · Apple M4 Pro

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

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

Global Score
88 vs 81
Hardware Fit
86 vs 100
Quality Score
89 vs 73

Hardware

gemma4:12b-it-qat gemma3n:latest
MachineMac miniSupermicro AS -2015HS-TNR
CPUApple M4 ProAMD EPYC 9654P 96-Core Processor
Cores1264
RAM24 GB128 GB
GPUApple M4 ProGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSmacOS 15.6.1Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:12b-it-qat gemma3n:latest
Tokens/sec30.0108.7
First chunk686 ms333 ms
TTFT7.1 s333 ms
Load time5.4 s4.5 s
Memory usage7.1 GB8.6 GB
Memory %30%7%

HW Fit Score Breakdown

gemma4:12b-it-qat

Speed
50/50
TTFT
6/20
Memory
30/30

gemma3n:latest

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

Quality

gemma4:12b-it-qat

Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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