phi3:14b

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

mistral:latest

llama · 7.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

63 vs 73

Hardware Fit

83 vs 96

Quality Score

55 vs 63

Hardware

phi3:14b mistral:latest

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

phi3:14b mistral:latest

Tokens/sec12.722.5

TTFT434 ms257 ms

Load time0.9 s0.6 s

Memory usage17.7 GB10.1 GB

Memory %55%32%

HW Fit Score Breakdown

phi3:14b

Speed

23/40

TTFT

30/30

Memory

30/30

mistral:latest

Speed

36/40

TTFT

30/30

Memory

30/30

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

mistral:latest

Reasoning

8/20

Coding

12/20

Instruction

15/20

Structured

14/15

Math

5/15

Multilingual

9/10

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

View phi3:14b details | View mistral:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running