google/gemma-3-12b

gemma3 · 12B · 4bit

Good

Mar 3, 2026 · Apple M4

vicuna:7b

llama · 7B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score

77 vs 59

Hardware Fit

72 vs 97

Quality Score

79 vs 43

Hardware

google/gemma-3-12b vicuna:7b

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 vicuna:7b

Tokens/sec7.923.4

TTFT1.8 s242 ms

Load time0.0 s0.4 s

Memory usage0.0 GB5.8 GB

Memory %0%18%

HW Fit Score Breakdown

google/gemma-3-12b

Speed

14/40

TTFT

28/30

Memory

30/30

vicuna:7b

Speed

37/40

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

vicuna:7b

Reasoning

8/20

Coding

4/20

Instruction

10/20

Structured

12/15

Math

2/15

Multilingual

7/10

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

View google/gemma-3-12b details | View vicuna:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running