gemma4:31b
OLLAMA GGUFgemma4 · 30.7B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
Global Score
64 vs 89
Hardware Fit
41 vs 96
Quality Score
74 vs 86
Hardware
gemma4:31b qwen3-coder:30b
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M4 Max
Cores3216
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 3090Apple M4 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.5.1
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:31b qwen3-coder:30b
Tokens/sec9.589.9
First chunk1751 ms188 ms
TTFT30.0 s188 ms
Load time33.9 s4.0 s
Memory usage1.4 GB30.2 GB
Memory %4%47%
HW Fit Score Breakdown
gemma4:31b
Speed
11/50
TTFT
0/20
Memory
30/30
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
gemma4:31b
Reasoning
11/20
Coding
17/20
Instruction
10/20
Structured
15/15
Math
12/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:30b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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