starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
gemma4:e2b
OLLAMA GGUFgemma4 · 4.6B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
39 vs 93
Hardware Fit
100 vs 100
Quality Score
13 vs 90
Hardware
starcoder2:3b gemma4:e2b
MachineMacBook AirMicrosoft WSL
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM32 GB8 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
starcoder2:3b gemma4:e2b
Tokens/sec49.4141.2
First chunkN/A94 ms
TTFT155 ms1.6 s
Load time0.4 s18.4 s
Memory usage3.0 GB0.2 GB
Memory %9%3%
HW Fit Score Breakdown
starcoder2:3b
Speed
40/50
TTFT
30/20
Memory
30/30
gemma4:e2b
Speed
50/50
TTFT
20/20
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:e2b
Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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