starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
35 vs 50
Hardware Fit
100 vs 97
Quality Score
7 vs 30
Hardware
starcoder2:3b gemma3:270m
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M3 Pro
Cores612
RAM7 GB36 GB
GPUIntegrated / UnknownApple M3 Pro
OSUbuntu 22.04.5 LTSmacOS 15.7.5
Archarm64arm64
Power Modebalancedbalanced
Performance
starcoder2:3b gemma3:270m
Tokens/sec31.5239.2
First chunk392 ms127 ms
TTFT392 ms127 ms
Load time4.8 s0.7 s
Memory usage1.8 GB0.6 GB
Memory %24%2%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
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
gemma3:270m
Reasoning
4/20
Coding
2/20
Instruction
10/20
Structured
8/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak
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