qwen2.5:0.5b

qwen2 · 494.03M · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

qwen3:1.7b

qwen3 · 2.0B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

59 vs 70

Hardware Fit

99 vs 87

Quality Score

33 vs 59

Hardware

qwen2.5:0.5b qwen3:1.7b

MachineMacBook Air—

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5:0.5b qwen3:1.7b

Tokens/sec162.737.9

TTFT81 ms3.1 s

Load time0.5 s1.2 s

Memory usage1.7 GB4.9 GB

Memory %5%15%

HW Fit Score Breakdown

qwen2.5:0.5b

Speed

40/40

TTFT

30/30

Memory

29/30

qwen3:1.7b

Speed

40/40

TTFT

17/30

Memory

30/30

Quality

qwen2.5:0.5b

Reasoning

6/20

Coding

0/20

Instruction

7/20

Structured

11/15

Math

5/15

Multilingual

4/10

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

qwen3:1.7b

Reasoning

16/20

Coding

0/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

View qwen2.5:0.5b details | View qwen3:1.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running