gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor
Global Score
33 vs 78
Hardware Fit
50 vs 86
Quality Score
25 vs 74
Hardware
gemma4:26b qwen3:8b
MachineMac mini—
CPUApple M4AMD Ryzen 9 3900X 12-Core Processor
Cores1024
RAM24 GB64 GB
GPUApple M4NVIDIA GeForce RTX 4060 Ti
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:26b qwen3:8b
Tokens/sec20.048.5
First chunk941 ms202 ms
TTFT30.0 s4.3 s
Load time0.2 s4.2 s
Memory usage20.3 GB5.5 GB
Memory %85%9%
HW Fit Score Breakdown
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
qwen3:8b
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
qwen3:8b
Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate 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