gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
Global Score
89 vs 35
Hardware Fit
88 vs 100
Quality Score
89 vs 7
Hardware
gemma4:12b starcoder2:3b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M2 ProCortex-A78AE
Cores106
RAM16 GB7 GB
GPUApple M2 ProIntegrated / Unknown
OSmacOS 26.5Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:12b starcoder2:3b
Tokens/sec18.431.5
First chunk758 ms392 ms
TTFT758 ms392 ms
Load time0.3 s4.8 s
Memory usage7.5 GB1.8 GB
Memory %47%24%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
starcoder2:3b
Reasoning
0/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest