gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Feb 28, 2026 · Apple M4
Global Score
89 vs 68
Hardware Fit
88 vs 98
Quality Score
89 vs 55
Hardware
gemma4:12b gemma3:1b
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedunknown
Performance
gemma4:12b gemma3:1b
Tokens/sec18.539.5
First chunk752 msN/A
TTFT752 ms333 ms
Load time6.1 s1.6 s
Memory usage7.5 GB1.3 GB
Memory %47%4%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
gemma3:1b
Speed
40/50
TTFT
30/20
Memory
28/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma3:1b
Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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