gemma2:9b

gemma2 · 9.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

wizardlm2:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

69 vs 65

Hardware Fit

89 vs 97

Quality Score

56 vs 43

Hardware

gemma2:9b wizardlm2:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

gemma2:9b wizardlm2:7b

Tokens/sec16.823.2

TTFT372 ms264 ms

Load time0.8 s0.6 s

Memory usage8.2 GB9.9 GB

Memory %26%31%

HW Fit Score Breakdown

gemma2:9b

Speed

29/40

TTFT

30/30

Memory

30/30

wizardlm2:7b

Speed

37/40

TTFT

30/30

Memory

30/30

Quality

gemma2:9b

Reasoning

11/20

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

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 gemma2:9b details | View wizardlm2:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running