gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
89 vs 77
Hardware Fit
88 vs 74
Quality Score
89 vs 78
Hardware
gemma4:12b phi4:14b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M2 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M2 ProDevice 2e12
OSmacOS 26.5Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
gemma4:12b phi4:14b
Tokens/sec18.522.9
First chunk752 ms198 ms
TTFT752 ms198 ms
Load time6.1 s10.3 s
Memory usage7.5 GB14.7 GB
Memory %47%12%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
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
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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