openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · Q4_K_M
Jul 7, 2026 · AMD Ryzen 7 5800H
Global Score
91 vs 68
Hardware Fit
90 vs 93
Quality Score
91 vs 57
Hardware
openai/gpt-oss-20b google/gemma-4-e4b
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 google/gemma-4-e4b
Tokens/sec95.126.2
First chunk3 ms17 ms
TTFT2.5 s572 ms
Load time9.2 sN/A
Memory usage0.0 GB6.5 GB
Memory %0%41%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
google/gemma-4-e4b
Speed
46/50
TTFT
20/20
Memory
27/30
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
google/gemma-4-e4b
Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor
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