gemma3:12b

gemma3 · 12.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

qwen3.5:2b

qwen35 · 2.3B · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

67 vs 77

Hardware Fit

79 vs 100

Quality Score

59 vs 62

Hardware

gemma3:12b qwen3.5:2b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

gemma3:12b qwen3.5:2b

Tokens/sec12.330.4

TTFT656 ms215 ms

Load time5.5 s1.8 s

Memory usage11.0 GB4.5 GB

Memory %34%14%

HW Fit Score Breakdown

gemma3:12b

Speed

19/40

TTFT

30/30

Memory

30/30

qwen3.5:2b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

gemma3:12b

Reasoning

14/20

Coding

0/20

Instruction

13/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

qwen3.5:2b

Reasoning

12/20

Coding

10/20

Instruction

13/20

Structured

14/15

Math

4/15

Multilingual

9/10

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

View gemma3:12b details | View qwen3.5:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running