starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 7, 2026 · Cortex-X925
Global Score
39 vs 77
Hardware Fit
100 vs 59
Quality Score
13 vs 84
Hardware
starcoder2:3b gemma4:12b
MachineMacBook AirASUSTeK COMPUTER INC. GX10
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
starcoder2:3b gemma4:12b
Tokens/sec49.426.8
First chunkN/A632 ms
TTFT155 ms30.0 s
Load time0.4 s5.4 s
Memory usage3.0 GB9.3 GB
Memory %9%8%
HW Fit Score Breakdown
starcoder2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
gemma4:12b
Speed
29/50
TTFT
0/20
Memory
30/30
Quality
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
gemma4:12b
Reasoning
17/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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