gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Jul 7, 2026 · Cortex-X925
nemotron3:33b
OLLAMA GGUFnemotron_h_omni · 33.0B · Q4_K_M
Jun 28, 2026 · AMD RYZEN AI MAX+ 395
Global Score
94 vs 96
Hardware Fit
100 vs 95
Quality Score
92 vs 97
Hardware
gemma4:26b nemotron3:33b
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 Modeperformancelow-power
Performance
gemma4:26b nemotron3:33b
Tokens/sec67.462.7
First chunk529 ms372 ms
TTFT529 ms1.0 s
Load time6.0 s13.1 s
Memory usage17.6 GB24.4 GB
Memory %15%20%
HW Fit Score Breakdown
gemma4:26b
Speed
50/50
TTFT
20/20
Memory
30/30
nemotron3:33b
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
gemma4:26b
Reasoning
18/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
nemotron3:33b
Reasoning
19/20
Coding
18/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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