phi4:14b

phi3 · 14.7B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

codellama:7b

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

65 vs 68

Hardware Fit

77 vs 97

Quality Score

57 vs 49

Hardware

phi4:14b codellama:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

phi4:14b codellama:7b

Tokens/sec11.123.6

TTFT515 ms297 ms

Load time9.3 s0.9 s

Memory usage13.4 GB12.6 GB

Memory %42%39%

HW Fit Score Breakdown

phi4:14b

Speed

17/40

TTFT

30/30

Memory

30/30

codellama:7b

Speed

37/40

TTFT

30/30

Memory

30/30

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

codellama:7b

Reasoning

6/20

Coding

7/20

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 phi4:14b details | View codellama:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running