winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
77 vs 88
Hardware Fit
38 vs 86
Quality Score
93 vs 89
Hardware
winnow-12b gemma4:12b-it-qat
MachineGMKtec EVO-X3Mac mini
CPUAMD RYZEN AI MAX+ 395Apple M4 Pro
Cores3212
RAM120 GB24 GB
GPUAMD Radeon(TM) 8060S GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
winnow-12b gemma4:12b-it-qat
Tokens/sec12.930.0
First chunk19 ms686 ms
TTFT9.7 s7.1 s
Load time86.2 s5.4 s
Memory usage51.3 GB7.1 GB
Memory %43%30%
HW Fit Score Breakdown
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
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
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
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