openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 19, 2026 · Apple M4
winnow-12b
LM-STUDIO GGUFgemma4 · 12B · Q8_0
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
77 vs 77
Hardware Fit
67 vs 38
Quality Score
81 vs 93
Hardware
openai/gpt-oss-20b winnow-12b
MachineMac miniGMKtec EVO-X3
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB120 GB
GPUApple M4AMD Radeon(TM) 8060S Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b winnow-12b
Tokens/sec30.512.9
First chunk18 ms19 ms
TTFT30.0 s9.7 s
Load timeN/A86.2 s
Memory usage15.8 GB51.3 GB
Memory %66%43%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
0/20
Memory
17/30
winnow-12b
Speed
11/50
TTFT
0/20
Memory
27/30
Quality
openai/gpt-oss-20b
Reasoning
19/20
Coding
11/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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