phi4-mini
Mar 1, 2026 · Apple M4
starcoder2:3b
starcoder2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
39 vs 48
Hardware Fit
66 vs 100
Quality Score
21 vs 13
Hardware
phi4-mini starcoder2:3b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
phi4-mini starcoder2:3b
Tokens/sec21.849.4
TTFT9.6 s155 ms
Load time3.5 s0.4 s
Memory usage0.0 GB3.0 GB
Memory %0%9%
HW Fit Score Breakdown
phi4-mini
Speed
31/40
TTFT
5/30
Memory
30/30
starcoder2:3b
Speed
40/40
TTFT
30/30
Memory
30/30
Quality
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
starcoder2:3b
Reasoning
0/20
Coding
2/20
Instruction
5/20
Structured
2/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
Run yours and compare
npx metrillm@latest benchRequires Node 20+ and Ollama or LM Studio running