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

qwen3.8:27b-bf16

OLLAMA GGUF

qwen35 · 27.3B · BF16

Excellent

Aug 22, 2026 · AMD EPYC 7713 64-Core Processor

Global Score
84 vs 85
Hardware Fit
65 vs 77
Quality Score
92 vs 88

Hardware

openai/gpt-oss-20b qwen3.8:27b-bf16
MachineASUSDell Inc. PowerEdge XE8545
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD EPYC 7713 64-Core Processor
Cores16128
RAM31 GB1007 GB
GPUNVIDIA GeForce RTX 4090, RaphaelGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OScachyos rollingRocky Linux 8.10
Archx64x64
Power Modeperformanceunknown

Performance

openai/gpt-oss-20b qwen3.8:27b-bf16
Tokens/sec221.527.2
First chunk5 ms237 ms
TTFT30.0 s237 ms
Load timeN/A43.8 s
Memory usage21.1 GB68.8 GB
Memory %69%7%

HW Fit Score Breakdown

openai/gpt-oss-20b

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

qwen3.8:27b-bf16

Speed
27/50
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

qwen3.8:27b-bf16

Reasoning
18/20
Coding
18/20
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
View openai/gpt-oss-20b details | View qwen3.8:27b-bf16 details

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