openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
91 vs 79
Hardware Fit
90 vs 47
Quality Score
91 vs 93
Hardware
openai/gpt-oss-20b GPT-120B:120b
MachineMacBook ProHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M3 MaxIntel Core™ i7-14700F
Cores1628
RAM128 GB128 GB
GPUApple M3 MaxNVIDIA GeForce RTX 5080
OSmacOS 27.2Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b GPT-120B:120b
Tokens/sec95.118.2
First chunk3 ms1719 ms
TTFT2.5 s3.9 s
Load time9.2 s50.9 s
Memory usage0.0 GB61.5 GB
Memory %0%48%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
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
GPT-120B:120b
Reasoning
19/20
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