gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
84 vs 88
Hardware Fit
80 vs 86
Quality Score
86 vs 89
Hardware
gemma4:26b gemma4:12b-it-qat
MachineSystem manufacturerMac mini
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M4 Pro
Cores3212
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 3090Apple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:26b gemma4:12b-it-qat
Tokens/sec147.630.0
First chunk139 ms686 ms
TTFT30.0 s7.1 s
Load time21.3 s5.4 s
Memory usage1.7 GB7.1 GB
Memory %5%30%
HW Fit Score Breakdown
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
gemma4:26b
Reasoning
17/20
Coding
14/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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