openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jun 5, 2026 · AMD Ryzen 7 5800H
Global Score
91 vs 89
Hardware Fit
90 vs 83
Quality Score
91 vs 92
Hardware
openai/gpt-oss-20b gemma4:latest
MachineMacBook ProLENOVO 82JQ
CPUApple M3 MaxAMD Ryzen 7 5800H
Cores1616
RAM128 GB16 GB
GPUApple M3 MaxNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 27.2Microsoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b gemma4:latest
Tokens/sec95.146.3
First chunk3 ms824 ms
TTFT2.5 s3.8 s
Load time9.2 s21.0 s
Memory usage0.0 GB8.9 GB
Memory %0%56%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
gemma4:latest
Speed
50/50
TTFT
11/20
Memory
22/30
Quality
openai/gpt-oss-20b
Reasoning
18/20
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
gemma4:latest
Reasoning
18/20
Coding
19/20
Instruction
15/20
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