Back to leaderboard

google/gemma-3-12b

gemma3 · 12B · 4bit

Good

Mar 3, 2026 · Apple M4

starcoder2:3b

starcoder2 · 3B · Q4_0

Not Rec.

Mar 2, 2026 · Apple M4

Global Score
77 vs 39
Hardware Fit
72 vs 100
Quality Score
79 vs 13

Hardware

google/gemma-3-12b starcoder2:3b
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 starcoder2:3b
Tokens/sec7.949.4
TTFT1.8 s155 ms
Load time0.0 s0.4 s
Memory usage0.0 GB3.0 GB
Memory %0%9%

HW Fit Score Breakdown

google/gemma-3-12b

Speed
14/40
TTFT
28/30
Memory
30/30

starcoder2:3b

Speed
40/40
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

starcoder2:3b

Reasoning
0/20
Coding
2/20
Instruction
5/20
Structured
2/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running