winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
77 vs 84
Hardware Fit
38 vs 80
Quality Score
93 vs 86
Hardware
winnow-12b gemma4:26b
MachineGMKtec EVO-X3System manufacturer
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 9 5950X 16-Core Processor
Cores3232
RAM120 GB32 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA GeForce RTX 3090
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced
Performance
winnow-12b gemma4:26b
Tokens/sec12.9147.6
First chunk19 ms139 ms
TTFT9.7 s30.0 s
Load time86.2 s21.3 s
Memory usage51.3 GB1.7 GB
Memory %43%5%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
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
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
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