mistral:7b

llama · 7.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

gemma2:9b

gemma2 · 9.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

75 vs 69

Hardware Fit

95 vs 89

Quality Score

62 vs 56

Hardware

mistral:7b gemma2:9b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistral:7b gemma2:9b

Tokens/sec22.016.8

TTFT261 ms372 ms

Load time0.7 s0.8 s

Memory usage10.1 GB8.2 GB

Memory %32%26%

HW Fit Score Breakdown

mistral:7b

Speed

35/40

TTFT

30/30

Memory

30/30

gemma2:9b

Speed

29/40

TTFT

30/30

Memory

30/30

Quality

mistral:7b

Reasoning

8/20

Coding

12/20

Instruction

15/20

Structured

14/15

Math

4/15

Multilingual

9/10

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

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

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

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running