google/gemma-3-12b

gemma3 · 12B · 4bit

Good

Mar 3, 2026 · Apple M4

llama2:13b

llama · 13B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

77 vs 56

Hardware Fit

72 vs 84

Quality Score

79 vs 44

Hardware

google/gemma-3-12b llama2:13b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

google/gemma-3-12b llama2:13b

Tokens/sec7.913.5

TTFT1.8 s415 ms

Load time0.0 s0.6 s

Memory usage0.0 GB10.3 GB

Memory %0%32%

HW Fit Score Breakdown

google/gemma-3-12b

Speed

14/40

TTFT

28/30

Memory

30/30

llama2:13b

Speed

24/40

TTFT

30/30

Memory

30/30

Quality

google/gemma-3-12b

Reasoning

13/20

Coding

19/20

Instruction

14/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

llama2:13b

Reasoning

9/20

Coding

3/20

Instruction

13/20

Structured

7/15

Math

3/15

Multilingual

9/10

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

View google/gemma-3-12b details | View llama2:13b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running