openai/gpt-oss-20b

gpt-oss · 20B · MXFP4

THINKING MODEL

ASUS (AMD Ryzen 5 5500)

31 GB · Nobara Linux 43

Tested on April 24, 2026

Top 4% Compare

Global Score

90 /100

Excellent

Hardware Fit

88/100

Quality

91/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: ASUS
CPU: AMD Ryzen 5 5500
Cores: 12 threads (6 cores)
Frequency: 3.49 GHz
RAM: 31 GB
GPU: Navi 44 [Radeon RX 9060 XT]
OS: Nobara Linux 43
Arch: x64
Power Mode: performance

Performance

Tokens/sec Tokens generated per second — higher is better: 58.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 6 ms
Time to first token How fast the model starts responding — lower is better: 4.5 s
Load time Time to load the model into memory before inference: N/A
Memory usage RAM consumed during inference — percentage of total system memory: 11.9 GB (38%)
Total tokens Total number of tokens generated across all benchmark prompts: 1713
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~896

Score breakdown

Speed

50/50

Time to first token

10/20

Memory

28/30

Quality

Reasoning

18/20

Coding

15/20

Instruction following

18/20

Structured output

15/15

Math

15/15

Multilingual

10/10

Category levels

Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.12+1
Model format: GGUF
Hardware profile: BALANCED
Result hash: b95880a90fa879c0b1cf3c575e45f68965f7b471603615e2c952c5a9a504a8fd

Interpretation

Hardware fit: 88/100. Overall suitability: EXCELLENT (Global 90/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Model memory footprint is estimated via LM Studio CLI rather than measured from a fresh load.

Bench Environment

Thermal: nominal CPU load: avg 22% (peak 27%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest