winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
77 vs 84
Hardware Fit
38 vs 69
Quality Score
93 vs 91
Hardware
winnow-12b gptoss · 20.9B · M…
MachineGMKtec EVO-X3Mac Pro
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-10400
Cores3212
RAM120 GB32 GB
GPUAMD Radeon(TM) 8060S GraphicsAMD Radeon RX 6700 XT
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.5.1
Archx64x64
Power Modebalancedbalanced
Performance
winnow-12b gptoss · 20.9B · M…
Tokens/sec12.917.5
First chunk19 ms643 ms
TTFT9.7 s7.7 s
Load time86.2 s0.0 s
Memory usage51.3 GB0.8 GB
Memory %43%3%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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