# LLM-Benchmark Konfiguration # Modell : gpt-oss-20b # Engine : vLLM # Run-ID : run-20260723-045447-95795b # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ vllm serve openai/gpt-oss-20b \ --served-model-name gpt-oss-20b \ --dtype auto \ --max-model-len 8192 \ --gpu-memory-utilization 0.92 \ --trust-remote-code \ --host 0.0.0.0 \ --port 8000

Engine?Die Inferenz-Software, die das Modell ausliefert (z.B. vLLM oder llama.cpp). Sie bestimmt Geschwindigkeit, unterstuetzte Modellformate und welche Parameter ueberhaupt verfuegbar sind.	vllm
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.	gpt-oss-20b
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.	gpt-oss-20b
Dtype?Zahlenformat der Modellgewichte bei der Berechnung (z.B. auto, float16, bfloat16). 'auto' waehlt automatisch das vom Modell empfohlene Format.	auto
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	8192
GPU-Speicher?Anteil des GPU-Speichers (0 bis 1), den vLLM belegen darf. 0.92 = 92 %. Hoeher = mehr Platz fuer den KV-Cache (mehr/laengere parallele Anfragen), aber groesseres Risiko fuer 'Out of Memory'.	0.92

All benchmarks of this model To leaderboard

Model comparison

gpt-oss-20b on various hardware

All published performance runs of this model – each bubble a variant: position = prefill (X) × generation (Y), bubble size = number of runs. Closer to the top right = faster. ★ Marked gold = this benchmark.

GPUby graphics card

NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.995,4 tok/s★ NVIDIA GeForce RTX 5090 1.890,7 tok/s this runNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.835,7 tok/sNVIDIA GeForce RTX 5070 Ti 1.210,3 tok/sNVIDIA GeForce RTX 3090 Ti 1.113,5 tok/sNVIDIA RTX A6000 703,8 tok/sAMD Radeon PRO W7900 Dual Slot 344,1 tok/sAMD Radeon PRO W7800 48GB 280,0 tok/sNVIDIA GB10 (DGX Spark) 202,1 tok/sAMD Radeon AI PRO R9700 163,6 tok/sNVIDIA Tesla P100 PCIe 16GB 111,1 tok/sAMD Radeon 8060S Graphics 74,4 tok/sCPU-only 70,9 tok/sNVIDIA GeForce RTX 2060 14,5 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.995,4 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 1.890,7 tok/s this runAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.835,7 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 1.210,3 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 1.113,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 703,8 tok/sAMD Ryzen 5 5600X 6-Core Processor 572,1 tok/sNVIDIA Grace 202,1 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 111,1 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 74,4 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 14,5 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.995,4 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.890,7 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.835,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1.210,3 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 1.113,5 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 572,1 tok/sASUSTeK COMPUTER INC. GX10 202,1 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 111,1 tok/sBosgame AXB35-02 (BeyondMax Series) 74,4 tok/sDell Inc. PowerEdge R820 14,5 tok/s

ENGby engine

llama.cpp 1.995,4 tok/s★ vLLM 1.443,9 tok/s this rununbekannt 147,8 tok/s

DRVby driver

unbekannt 1.995,4 tok/sNVIDIA 590.48.01 / CUDA 13.1 202,1 tok/sAMD 7.0.0-27-generic 147,8 tok/s

💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× concurrent). Methodology →

⚙️ ConfigurationAll metrics and charts below follow these settings – based on a 24-month runtime.Save to URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 72 W

⚡ TDP 622 W

☁️ External LLM (API) show

Input €/1M Output €/1M Input per output token

Electricity0.30 EUR/kWh

Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load

Avg cost / hourEUR 0.19

Electricity / 1M tokensEUR 0.19

Token / kWh1.55M

Acquisition (system)EUR 4,986 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 1,008 · PSU EUR 180

Electricity (2 years)–

TCO (2 years)EUR 8,253

Output tokens (2 years)16.84B

☁️ External LLM (API) – comparison

External LLM cost (2 years)–

Savings vs. external (2 years)–

All values above and the charts below take the configured system utilization into account: at X% the system generates only X% of the time, the rest it idles (72 W). Cost per hour drops (more idle), cost per token rises.

Cost over 2 years – electricity only

Cost over 2 years – incl. acquisition (TCO)

Speed vs. tokens per euro

Euro per 1M tokens

Comparison vs. API – economics per benchmark

	gpt-oss-20bNVIDIA GeForce RTX 5090	gpt-oss-20bNVIDIA GeForce RTX 5090	gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gpt-oss-20bNVIDIA GeForce RTX 5090
Electricity cost (24 mo.)	–	–	–	–
Acquisition cost	–	–	–	–
Total cost (TCO)	–	–	–	–
Generated tokens (24 mo.)	–	–	–	–
Token price via API	–	–	–	–
Break-even point (days)	–	–	–	–
Result (savings / extra cost)	–	–	–	–

NVIDIA GeForce RTX 5090 · this run 267 tok/s NVIDIA GeForce RTX 5090 405 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 395 tok/s NVIDIA GeForce RTX 5090 389 tok/s

Comparison with up to 3 next-best runs of this model at the same concurrency (at least one on different hardware). Power = GPU TDP + CPU (idle + 15 %) + board (estimated), acquisition = full system (GPU + CPU + board + RAM + PSU), prices = stored market prices.

Contributed by

Mario Alka Administrator

@marioalka

Ich bin Unternehmer, Softwareentwickler und KI-Enthusiast. Seit vielen Jahren entwickle ich Unternehmenssoftware und beschäftige mich inzwischen fast täglich mit lokalen LLMs, KI-Agenten und leistungsfähiger KI-Hardware.

Mit LLM-Benchmark.de möchte ich eine Plattform schaffen, auf der Modelle, GPUs und Agenten objektiv und reproduzierbar miteinander verglichen werden.