vicuna:13b

llama · 13B · Q4_0

Good

Mar 1, 2026 · Apple M4

phi3:14b

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

62 vs 66

Hardware Fit

84 vs 83

Quality Score

48 vs 55

Hardware

vicuna:13b phi3:14b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

vicuna:13b phi3:14b

Tokens/sec13.412.7

TTFT438 ms434 ms

Load time0.6 s0.9 s

Memory usage10.3 GB17.7 GB

Memory %32%55%

HW Fit Score Breakdown

vicuna:13b

Speed

24/40

TTFT

30/30

Memory

30/30

phi3:14b

Speed

23/40

TTFT

30/30

Memory

30/30

Quality

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

phi3:14b

Reasoning

14/20

Coding

2/20

Instruction

14/20

Structured

7/15

Math

8/15

Multilingual

10/10

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

View vicuna:13b details | View phi3:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running