gemma2:9b

gemma2 · 9.2B · Q4_0

Good

Mar 2, 2026 · Apple M4

orca-mini:7b

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

78 vs 61

Hardware Fit

89 vs 98

Quality Score

71 vs 37

Hardware

gemma2:9b orca-mini: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 orca-mini:7b

Tokens/sec17.524.4

TTFT347 ms219 ms

Load time0.8 s0.4 s

Memory usage8.2 GB5.8 GB

Memory %26%18%

HW Fit Score Breakdown

gemma2:9b

Speed

29/40

TTFT

30/30

Memory

30/30

orca-mini:7b

Speed

38/40

TTFT

30/30

Memory

30/30

Quality

gemma2:9b

Reasoning

11/20

Coding

15/20

Instruction

13/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

orca-mini:7b

Reasoning

8/20

Coding

1/20

Instruction

8/20

Structured

10/15

Math

2/15

Multilingual

8/10

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

View gemma2:9b details | View orca-mini:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running