qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 18, 2026 · AMD Ryzen 5 5500U
gemma3:270m
OLLAMA GGUFgemma3 · 268.10M · Q8_0
Mar 5, 2026 · Apple M3 Pro
Global Score
82 vs 50
Hardware Fit
71 vs 97
Quality Score
87 vs 30
Hardware
qwen3-coder:30b gemma3:270m
MachineHP HP Pavilion Laptop 15-eh1xxxMacBook Pro
CPUAMD Ryzen 5 5500UApple M3 Pro
Cores1212
RAM63 GB36 GB
GPUAMD Radeon(TM) GraphicsApple M3 Pro
OSMicrosoft Windows 10 Enterprise LTSC 10.0.19044macOS 15.7.5
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3-coder:30b gemma3:270m
Tokens/sec14.3239.2
First chunk869 ms127 ms
TTFT869 ms127 ms
Load time0.3 s0.7 s
Memory usage20.5 GB0.6 GB
Memory %32%2%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
22/50
TTFT
20/20
Memory
29/30
gemma3:270m
Speed
50/50
TTFT
20/20
Memory
27/30
Quality
qwen3-coder:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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