phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
77 vs 63
Hardware Fit
74 vs 62
Quality Score
78 vs 63
Hardware
phi4:14b gemma4:12b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
phi4:14b gemma4:12b
Tokens/sec22.915.3
First chunk198 ms1142 ms
TTFT198 ms30.0 s
Load time10.3 s5.4 s
Memory usage14.7 GB7.6 GB
Memory %12%47%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
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
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