winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
google/gemma-4-26b-a4b-it-qat
LM-STUDIO GGUFgemma4 · 26B · Q4_0
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
77 vs 82
Hardware Fit
38 vs 56
Quality Score
93 vs 93
Hardware
winnow-12b google/gemma-4-26b…
MachineGMKtec EVO-X3Docker Container
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i9-11900H
Cores3216
RAM120 GB15 GB
GPUAMD Radeon(TM) 8060S GraphicsTigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26300Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance
Performance
winnow-12b google/gemma-4-26b…
Tokens/sec12.912.0
First chunk19 ms86 ms
TTFT9.7 s2.8 s
Load time86.2 s57.2 s
Memory usage51.3 GB9.1 GB
Memory %43%59%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
google/gemma-4-26b-a4b-…
Speed
22/50
TTFT
14/20
Memory
20/30
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
google/gemma-4-26b-a4b-…
Reasoning
17/20
Coding
19/20
Instruction
20/20
Structured
14/15
Math
13/15
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