gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
gemma4:e4b
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
66 vs 84
Hardware Fit
40 vs 98
Quality Score
77 vs 78
Hardware
gemma4:31b gemma4:e4b
MachineASUSTeK COMPUTER INC. GX10AZW GTR Pro
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB125 GB
GPUDevice 2e12Radeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modeperformanceperformance
Performance
gemma4:31b gemma4:e4b
Tokens/sec10.753.0
First chunk983 ms214 ms
TTFT20.3 s214 ms
Load time8.8 s3.1 s
Memory usage21.4 GB15.0 GB
Memory %18%12%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
0/20
Memory
30/30
gemma4:e4b
Speed
48/50
TTFT
20/20
Memory
30/30
Quality
gemma4:31b
Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:e4b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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