gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 77
Hardware Fit
80 vs 38
Quality Score
89 vs 93
Hardware
gemma4:12b winnow-12b
MachineASUSGMKtec EVO-X3
CPUIntel Gen Intel® Core™ i7-12700AMD RYZEN AI MAX+ 395
Cores2032
RAM30 GB120 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060AMD Radeon(TM) 8060S Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modelow-powerbalanced
Performance
gemma4:12b winnow-12b
Tokens/sec74.412.9
First chunk152 ms19 ms
TTFT30.0 s9.7 s
Load time0.0 s86.2 s
Memory usage0.8 GB51.3 GB
Memory %3%43%
HW Fit Score Breakdown
gemma4:12b
Speed
50/50
TTFT
0/20
Memory
30/30
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
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
winnow-12b
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
12/15
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