gemma3:12b

gemma3 · 12.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

67 vs 70

Hardware Fit

79 vs 99

Quality Score

59 vs 51

Hardware

gemma3:12b qwen3.5:0.8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

gemma3:12b qwen3.5:0.8b

Tokens/sec12.348.2

TTFT656 ms195 ms

Load time5.5 s1.0 s

Memory usage11.0 GB2.5 GB

Memory %34%8%

HW Fit Score Breakdown

gemma3:12b

Speed

19/40

TTFT

30/30

Memory

30/30

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

gemma3:12b

Reasoning

14/20

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

qwen3.5:0.8b

Reasoning

9/20

Coding

6/20

Instruction

11/20

Structured

13/15

Math

5/15

Multilingual

7/10

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

View gemma3:12b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running