gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
nemotron3:33b
OLLAMA GGUFnemotron_h_omni · 33.0B · Q4_K_M
Jun 28, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 96
Hardware Fit
80 vs 95
Quality Score
89 vs 97
Hardware
gemma4:12b nemotron3:33b
MachineASUSAZW GTR Pro
CPUIntel Gen Intel® Core™ i7-12700AMD RYZEN AI MAX+ 395
Cores2032
RAM30 GB125 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060Radeon 8060S
OSUbuntu 26.04.1 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power
Performance
gemma4:12b nemotron3:33b
Tokens/sec74.462.7
First chunk152 ms372 ms
TTFT30.0 s1.0 s
Load time0.0 s13.1 s
Memory usage0.8 GB24.4 GB
Memory %3%20%
HW Fit Score Breakdown
gemma4:12b
Speed
50/50
TTFT
0/20
Memory
30/30
nemotron3:33b
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
gemma4:12b
Reasoning
18/20
Coding
15/20
Instruction
17/20
Structured
15/15
Math
14/15
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