qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

qwen2.5:7b

qwen2 · 7.6B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

Global Score

61 vs 84

Hardware Fit

100 vs 95

Quality Score

44 vs 79

Hardware

qwen3:0.6b qwen2.5:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3:0.6b qwen2.5:7b

Tokens/sec144.322.2

TTFT81 ms285 ms

Load time0.9 s0.8 s

Memory usage4.1 GB7.6 GB

Memory %13%24%

HW Fit Score Breakdown

qwen3:0.6b

Speed

40/40

TTFT

30/30

Memory

30/30

qwen2.5:7b

Speed

35/40

TTFT

30/30

Memory

30/30

Quality

qwen3:0.6b

Reasoning

6/20

Coding

4/20

Instruction

10/20

Structured

13/15

Math

6/15

Multilingual

5/10

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

qwen2.5:7b

Reasoning

14/20

Coding

18/20

Instruction

16/20

Structured

14/15

Math

8/15

Multilingual

9/10

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

View qwen3:0.6b details | View qwen2.5:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running