qwen2.5:0.5b

qwen2 · 494.03M · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

gemma3:1b

gemma3 · 999.89M · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

59 vs 61

Hardware Fit

99 vs 90

Quality Score

33 vs 42

Hardware

qwen2.5:0.5b gemma3:1b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

qwen2.5:0.5b gemma3:1b

Tokens/sec162.787.9

TTFT81 ms2.3 s

Load time0.5 s0.2 s

Memory usage1.7 GB1.3 GB

Memory %5%4%

HW Fit Score Breakdown

qwen2.5:0.5b

Speed

40/40

TTFT

30/30

Memory

29/30

gemma3:1b

Speed

40/40

TTFT

20/30

Memory

30/30

Quality

qwen2.5:0.5b

Reasoning

6/20

Coding

0/20

Instruction

7/20

Structured

11/15

Math

5/15

Multilingual

4/10

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

gemma3:1b

Reasoning

6/20

Coding

0/20

Instruction

15/20

Structured

12/15

Math

1/15

Multilingual

8/10

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

View qwen2.5:0.5b details | View gemma3:1b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running