phi4:14b

phi3 · 14.7B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

smollm2:360m

llama · 361.82M · F16

Marginal

Mar 1, 2026 · Apple M4

Global Score

65 vs 58

Hardware Fit

77 vs 99

Quality Score

57 vs 30

Hardware

phi4:14b smollm2:360m

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

phi4:14b smollm2:360m

Tokens/sec11.1115.1

TTFT515 ms39 ms

Load time9.3 s0.4 s

Memory usage13.4 GB1.2 GB

Memory %42%4%

HW Fit Score Breakdown

phi4:14b

Speed

17/40

TTFT

30/30

Memory

30/30

smollm2:360m

Speed

40/40

TTFT

30/30

Memory

29/30

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

smollm2:360m

Reasoning

4/20

Coding

0/20

Instruction

10/20

Structured

9/15

Math

4/15

Multilingual

3/10

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

View phi4:14b details | View smollm2:360m details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running