qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

gemma3:12b

gemma3 · 12.2B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

Global Score

61 vs 80

Hardware Fit

100 vs 83

Quality Score

44 vs 78

Hardware

qwen3:0.6b gemma3:12b

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 gemma3:12b

Tokens/sec144.312.7

TTFT81 ms560 ms

Load time0.9 s2.8 s

Memory usage4.1 GB11.0 GB

Memory %13%34%

HW Fit Score Breakdown

qwen3:0.6b

Speed

40/40

TTFT

30/30

Memory

30/30

gemma3:12b

Speed

23/40

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

gemma3:12b

Reasoning

14/20

Coding

19/20

Instruction

13/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

View qwen3:0.6b details | View gemma3:12b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running