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
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
Global Score
91 vs 87
Hardware Fit
90 vs 75
Quality Score
91 vs 92
Hardware
openai/gpt-oss-20b gemma4:latest
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E47
CPUApple M3 MaxAMD Ryzen 9 9950X 16-Core Processor
Cores1632
RAM128 GB125 GB
GPUApple M3 MaxAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSmacOS 27.2Microsoft Windows 11 Pro 10.0.26100
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b gemma4:latest
Tokens/sec95.142.4
First chunk3 ms472 ms
TTFT2.5 s3.8 s
Load time9.2 s0.3 s
Memory usage0.0 GB12.3 GB
Memory %0%10%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
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
19/20
Coding
18/20
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