qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

google/gemma-3-12b

gemma3 · 12B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

61 vs 77

Hardware Fit

100 vs 72

Quality Score

44 vs 79

Hardware

qwen3:0.6b google/gemma-3-12b

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 google/gemma-3-12b

Tokens/sec144.37.9

TTFT81 ms1.8 s

Load time0.9 s0.0 s

Memory usage4.1 GB0.0 GB

Memory %13%0%

HW Fit Score Breakdown

qwen3:0.6b

Speed

40/40

TTFT

30/30

Memory

30/30

google/gemma-3-12b

Speed

14/40

TTFT

28/30

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

google/gemma-3-12b

Reasoning

13/20

Coding

19/20

Instruction

14/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

View qwen3:0.6b details | View google/gemma-3-12b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running