gemma3:12b

gemma3 · 12.2B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

wizardlm2:7b

llama · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

80 vs 59

Hardware Fit

83 vs 97

Quality Score

78 vs 43

Hardware

gemma3:12b wizardlm2:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

gemma3:12b wizardlm2:7b

Tokens/sec12.723.2

TTFT560 ms264 ms

Load time2.8 s0.6 s

Memory usage11.0 GB9.9 GB

Memory %34%31%

HW Fit Score Breakdown

gemma3:12b

Speed

23/40

TTFT

30/30

Memory

30/30

wizardlm2:7b

Speed

37/40

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

wizardlm2:7b

Reasoning

6/20

Coding

11/20

Instruction

10/20

Structured

4/15

Math

4/15

Multilingual

8/10

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

View gemma3:12b details | View wizardlm2:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running