openai/gpt-oss-20b
LM-STUDIO GGUFgpt-oss · 20B · MXFP4
Nov 9, 2026 · Apple M3 Max
Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
91 vs 88
Hardware Fit
90 vs 90
Quality Score
91 vs 87
Hardware
openai/gpt-oss-20b Qwen3-30B:30b
MachineMacBook ProGMKtec NucBox EVO-T2S
CPUApple M3 MaxIntel Core™ Ultra X7 358H
Cores1616
RAM128 GB64 GB
GPUApple M3 MaxIntel(R) Arc(TM) B390 GPU
OSmacOS 27.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
openai/gpt-oss-20b Qwen3-30B:30b
Tokens/sec95.131.3
First chunk3 ms560 ms
TTFT2.5 s560 ms
Load time9.2 s15.4 s
Memory usage0.0 GB17.7 GB
Memory %0%28%
HW Fit Score Breakdown
openai/gpt-oss-20b
Speed
50/50
TTFT
10/20
Memory
30/30
Qwen3-30B:30b
Speed
40/50
TTFT
20/20
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
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
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