gemma3:12b

gemma3 · 12.2B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

phi3:3.8b

phi3 · 3.8B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

80 vs 64

Hardware Fit

83 vs 100

Quality Score

78 vs 48

Hardware

gemma3:12b phi3:3.8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

gemma3:12b phi3:3.8b

Tokens/sec12.742.0

TTFT560 ms142 ms

Load time2.8 s1.1 s

Memory usage11.0 GB16.0 GB

Memory %34%50%

HW Fit Score Breakdown

gemma3:12b

Speed

23/40

TTFT

30/30

Memory

30/30

phi3:3.8b

Speed

40/40

TTFT

30/30

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

phi3:3.8b

Reasoning

12/20

Coding

3/20

Instruction

11/20

Structured

10/15

Math

5/15

Multilingual

7/10

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

View gemma3:12b details | View phi3:3.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running