gemma3:12b

gemma3 · 12.2B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score

80 vs 22

Hardware Fit

83 vs 50

Quality Score

78 vs 10

Hardware

gemma3:12b deepseek-r1:14b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

gemma3:12b deepseek-r1:14b

Tokens/sec12.711.4

TTFT560 ms30.0 s

Load time2.8 s1.0 s

Memory usage11.0 GB16.5 GB

Memory %34%52%

HW Fit Score Breakdown

gemma3:12b

Speed

23/40

TTFT

30/30

Memory

30/30

deepseek-r1:14b

Speed

20/40

TTFT

0/30

Memory

30/30

Quality

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

deepseek-r1:14b

Reasoning

1/20

Coding

3/20

Instruction

1/20

Structured

0/15

Math

0/15

Multilingual

5/10

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

View gemma3:12b details | View deepseek-r1:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running