Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO GGUF

gpt-oss · 20B · MXFP4

Not Rec.

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
84 vs 78
Hardware Fit
65 vs 54
Quality Score
92 vs 88

Hardware

openai/gpt-oss-20b qwen3-coder:30b-a3…
MachineASUSHP HP Pavilion Laptop 15-eh1xxx
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 5 5500U
Cores1612
RAM31 GB63 GB
GPUNVIDIA GeForce RTX 4090, RaphaelAMD Radeon(TM) Graphics
OScachyos rollingMicrosoft Windows 10 Enterprise LTSC 10.0.19044
Archx64x64
Power Modeperformancebalanced

Performance

openai/gpt-oss-20b qwen3-coder:30b-a3…
Tokens/sec221.58.0
First chunk5 ms1468 ms
TTFT30.0 s1.5 s
Load timeN/A114.5 s
Memory usage21.1 GB33.5 GB
Memory %69%53%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
15/30

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

Quality

openai/gpt-oss-20b

Reasoning
19/20
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-coder:30b-a3b-q8_0

Reasoning
17/20
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: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest