dolphin-phi:2.7b
phi2 · 3B · Q4_0
Mar 1, 2026 · Apple M4
phi4-mini
Mar 1, 2026 · Apple M4
Global Score
66 vs 39
Hardware Fit
100 vs 66
Quality Score
44 vs 21
Hardware
dolphin-phi:2.7b phi4-mini
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
dolphin-phi:2.7b phi4-mini
Tokens/sec56.121.8
TTFT108 ms9.6 s
Load time0.4 s3.5 s
Memory usage2.2 GB0.0 GB
Memory %7%0%
HW Fit Score Breakdown
dolphin-phi:2.7b
Speed
40/40
TTFT
30/30
Memory
30/30
phi4-mini
Speed
31/40
TTFT
5/30
Memory
30/30
Quality
dolphin-phi:2.7b
Reasoning
10/20
Coding
6/20
Instruction
12/20
Structured
2/15
Math
9/15
Multilingual
5/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Adequate
phi4-mini
Reasoning
11/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
5/15
Multilingual
5/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Weak
Run yours and compare
npx metrillm@latest benchRequires Node 20+ and Ollama or LM Studio running