starcoder2:3b
OLLAMA GGUFstarcoder2 · 3B · Q4_0
Jun 26, 2026 · Cortex-A78AE
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
35 vs 76
Hardware Fit
100 vs 46
Quality Score
7 vs 89
Hardware
starcoder2:3b gemma4:31b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M4 Max
Cores616
RAM7 GB64 GB
GPUIntegrated / UnknownApple M4 Max
OSUbuntu 22.04.5 LTSmacOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced
Performance
starcoder2:3b gemma4:31b
Tokens/sec31.522.4
First chunk392 ms565 ms
TTFT392 ms30.0 s
Load time4.8 s6.9 s
Memory usage1.8 GB43.9 GB
Memory %24%69%
HW Fit Score Breakdown
starcoder2:3b
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
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
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
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