phi3:14b

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

Global Score

66 vs 64

Hardware Fit

83 vs 56

Quality Score

55 vs 70

Hardware

phi3:14b llama3.1:8b

MachineMacBook AirMac Mini

CPUApple M4Apple M4 Pro

Cores1014

RAM32 GB64 GB

GPUApple M4Apple M4 Pro

OSmacOS 26.3macOS 15.7.4

Archarm64arm64

Power Modebalancedunknown

Performance

phi3:14b llama3.1:8b

Tokens/sec12.75.5

TTFT434 ms1.4 s

Load time0.9 s3.7 s

Memory usage17.7 GB28.6 GB

Memory %55%45%

HW Fit Score Breakdown

phi3:14b

Speed

23/40

TTFT

30/30

Memory

30/30

llama3.1:8b

Speed

5/40

TTFT

22/30

Memory

29/30

Quality

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

llama3.1:8b

Reasoning

12/20

Coding

17/20

Instruction

14/20

Structured

13/15

Math

4/15

Multilingual

10/10

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

View phi3:14b details | View llama3.1:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running