qwen2.5:14b

qwen2 · 14.8B · Q4_K_M

Excellent

Mar 1, 2026 · Apple M4

granite3.1-dense:2b

granite · 2.5B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

82 vs 72

Hardware Fit

80 vs 100

Quality Score

84 vs 54

Hardware

qwen2.5:14b granite3.1-dense:2b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5:14b granite3.1-dense:2b

Tokens/sec11.254.6

TTFT539 ms121 ms

Load time1.0 s0.4 s

Memory usage16.5 GB5.6 GB

Memory %52%18%

HW Fit Score Breakdown

qwen2.5:14b

Speed

20/40

TTFT

30/30

Memory

30/30

granite3.1-dense:2b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

qwen2.5:14b

Reasoning

17/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

10/15

Multilingual

10/10

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

granite3.1-dense:2b

Reasoning

8/20

Coding

9/20

Instruction

13/20

Structured

14/15

Math

3/15

Multilingual

7/10

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

View qwen2.5:14b details | View granite3.1-dense:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running