qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

gemma2:9b

gemma2 · 9.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

48 vs 69

Hardware Fit

53 vs 89

Quality Score

45 vs 56

Hardware

qwen3:4b gemma2:9b

Machine—MacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:4b gemma2:9b

Tokens/sec11.316.8

TTFT9.2 s372 ms

Load time0.1 s0.8 s

Memory usage7.2 GB8.2 GB

Memory %23%26%

HW Fit Score Breakdown

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

gemma2:9b

Speed

29/40

TTFT

30/30

Memory

30/30

Quality

qwen3:4b

Reasoning

4/20

Coding

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong 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 qwen3:4b details | View gemma2:9b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running