phi4-mini

Not Rec.

Mar 1, 2026 · Apple M4

vicuna:13b

llama · 13B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

39 vs 62

Hardware Fit

66 vs 84

Quality Score

21 vs 48

Hardware

phi4-mini vicuna:13b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

phi4-mini vicuna:13b

Tokens/sec21.813.4

TTFT9.6 s438 ms

Load time3.5 s0.6 s

Memory usage0.0 GB10.3 GB

Memory %0%32%

HW Fit Score Breakdown

phi4-mini

Speed

31/40

TTFT

5/30

Memory

30/30

vicuna:13b

Speed

24/40

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

vicuna:13b

Reasoning

7/20

Coding

5/20

Instruction

12/20

Structured

13/15

Math

3/15

Multilingual

8/10

Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

View phi4-mini details | View vicuna:13b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running