gpt-oss:20b

gptoss · 20.9B · MXFP4

THINKING MODEL

Framework Desktop (AMD Ryzen AI Max 300 Series) (AMD RYZEN AI MAX+ 395)

64 GB · Microsoft Windows 11 Pro for Workstations 10.0.26200

Tested on July 3, 2026 · Submitted by sapdev.eu

Top 2% Compare

Global Score

94 /100

Excellent

Hardware Fit

91/100

Quality

95/100

Get this model

🦙

Ollama

ollama pull gpt-oss:20b

View on Ollama Library

ollama.com/library/gpt-oss

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Framework Desktop (AMD Ryzen AI Max 300 Series)
CPU: AMD RYZEN AI MAX+ 395
Cores: 32 total (32 perf)
Frequency: 3 GHz
RAM: 64 GB LPDDR5
GPU: AMD Radeon(TM) 8060S Graphics
OS: Microsoft Windows 11 Pro for Workstations 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 48.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.4
First chunk latency Delay before the first streamed chunk arrives from runtime: 357 ms
Time to first token How fast the model starts responding — lower is better: 2.3 s
Load time Time to load the model into memory before inference: 0.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 16.4 GB (26%)
Total tokens Total number of tokens generated across all benchmark prompts: 1558
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~426

Score breakdown

Speed

50/50

Time to first token

11/20

Memory

30/30

Quality

Reasoning

19/20

Coding

19/20

Instruction following

17/20

Structured output

15/15

Math

15/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.1
Model format: GGUF
Hardware profile: HIGH-END
Result hash: da208937766c773d665202dee2a2bf2b1a8f828257a54d2247fa0281684edc4a

Interpretation

Hardware fit: 91/100. Overall suitability: EXCELLENT (Global 94/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

CPU load: avg 11% (peak 17%)

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