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

ornith-1.5-9b

LM-STUDIO GGUF

qwen35 · 9B · Q6_K

Excellent

Aug 21, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
84 vs 83
Hardware Fit
65 vs 100
Quality Score
92 vs 76

Hardware

openai/gpt-oss-20b ornith-1.5-9b
MachineASUSMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNVIDIA GeForce RTX 4090, RaphaelNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

openai/gpt-oss-20b ornith-1.5-9b
Tokens/sec221.5102.9
First chunk5 ms12 ms
TTFT30.0 s101 ms
Load timeN/AN/A
Memory usage21.1 GB6.8 GB
Memory %69%22%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

ornith-1.5-9b

Speed
50/50
TTFT
20/20
Memory
30/30

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

ornith-1.5-9b

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate 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