qwen2.5:1.5b

qwen2 · 1.5B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

llama2:13b

llama · 13B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

68 vs 60

Hardware Fit

99 vs 84

Quality Score

47 vs 44

Hardware

qwen2.5:1.5b llama2:13b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5:1.5b llama2:13b

Tokens/sec81.513.5

TTFT119 ms415 ms

Load time0.5 s0.6 s

Memory usage2.6 GB10.3 GB

Memory %8%32%

HW Fit Score Breakdown

qwen2.5:1.5b

Speed

40/40

TTFT

30/30

Memory

29/30

llama2:13b

Speed

24/40

TTFT

30/30

Memory

30/30

Quality

qwen2.5:1.5b

Reasoning

8/20

Coding

0/20

Instruction

12/20

Structured

13/15

Math

6/15

Multilingual

8/10

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

llama2:13b

Reasoning

9/20

Coding

3/20

Instruction

13/20

Structured

7/15

Math

3/15

Multilingual

9/10

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

View qwen2.5:1.5b details | View llama2:13b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running