winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
77 vs 84
Hardware Fit
38 vs 65
Quality Score
93 vs 92
Hardware
winnow-12b openai/gpt-oss-20b
MachineGMKtec EVO-X3ASUS
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 7800X3D 8-Core Processor
Cores3216
RAM120 GB31 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Pro 10.0.26300cachyos rolling
Archx64x64
Power Modebalancedperformance
Performance
winnow-12b openai/gpt-oss-20b
Tokens/sec12.9221.5
First chunk19 ms5 ms
TTFT9.7 s30.0 s
Load time86.2 sN/A
Memory usage51.3 GB21.1 GB
Memory %43%69%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
15/30
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
openai/gpt-oss-20b
Reasoning
19/20
Coding
15/20
Instruction
18/20
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