phi4:14b
phi3 · 14.7B · Q4_K_M
Mar 1, 2026 · Apple M4
granite3.1-dense:8b
granite · 8.2B · Q4_K_M
Mar 1, 2026 · Apple M4
Global Score
65 vs 76
Hardware Fit
77 vs 91
Quality Score
57 vs 66
Hardware
phi4:14b granite3.1-dense:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modeunknownbalanced
Performance
phi4:14b granite3.1-dense:8b
Tokens/sec11.118.8
TTFT515 ms308 ms
Load time9.3 s0.6 s
Memory usage13.4 GB13.0 GB
Memory %42%41%
HW Fit Score Breakdown
phi4:14b
Speed
17/40
TTFT
30/30
Memory
30/30
granite3.1-dense:8b
Speed
31/40
TTFT
30/30
Memory
30/30
Quality
phi4:14b
Reasoning
16/20
Coding
0/20
Instruction
11/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
granite3.1-dense:8b
Reasoning
12/20
Coding
11/20
Instruction
15/20
Structured
14/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
npx metrillm@latest benchRequires Node 20+ and Ollama or LM Studio running