Contributed byMario AlkaOpenAI gpt-oss-20b
Performance benchmark · measured on 24.07.2026 01:56
Benchmark-ID
run-20260724-082940-8305a5Timebench 3 - Kombi (Prefill + Generation)MoE20BRuntime: vLLM
⚠
Configuration note: Es sind 3 Grafikkarten installiert, aber nur 1 wurde fuer diesen Lauf genutzt (tensor-parallel-size=1). Mit allen 3 GPUs koennte der Durchsatz deutlich hoeher liegen.
Generation252,68tok/s
Prefill7.067,97tok/s
Time to First Token281,00ms
Total duration8,67s
Concurrency1parallel
Ranking in the field
45of 168 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 74 % of all comparable systems.
Generation
252,7 tok/s
+51 % vs Ø 167,1
Prefill
7.068,0 tok/s
+66 % vs Ø 4.270,2
Time to First Token
281 ms
-65 % vs Ø 794
Distribution in the field9 – 362 tok/s
Wie schlägt sich dieser Benchmark mit anderen Modellen?
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-a2f36d
356,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-1be57b
355,6 tok/s
gpt-oss-20b same model3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032120-b63d5d
350,7 tok/s
gpt-oss-20b same model3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-74868e
350,0 tok/s
gpt-oss-20b same model3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-120dc2
348,9 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184455-9cb45c
343,9 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105339-e213a2
331,0 tok/s
Nemotron-3-Nano-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-e34cf0
330,8 tok/s
Nemotron-Cascade-2-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-3ddb51
330,2 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105339-133b6a
330,1 tok/s
Nemotron-3-Nano-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105341-f734f1
330,0 tok/s
Nemotron-Cascade-2-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-508364
329,9 tok/s
gpt-oss-20b this run3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260724-082940-8305a5
252,7 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 1× concurrent · Generation (tok/s)
NVIDIA GeForce RTX 5090run-20260724-004608-16af9b
404,6 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260730-035052-9f766a
395,2 tok/s
NVIDIA GeForce RTX 5090run-20260724-004607-29bd16
388,9 tok/s
NVIDIA GeForce RTX 5090run-20260729-032121-1c779f
388,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032120-b63d5d
350,7 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032121-74868e
350,0 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-034052-120dc2
348,9 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032120-eb29ce
321,2 tok/s
NVIDIA GeForce RTX 5090run-20260724-004604-0c2a06
280,2 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260723-194447-636902
268,7 tok/s
NVIDIA GeForce RTX 5090run-20260723-045447-95795b
267,0 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition this runrun-20260724-082940-8305a5
252,7 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260724-004605-36d393
246,1 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260724-004605-845608
245,6 tok/s
Hardware
GPU: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE
Setup
Runtime: vLLM
Quantization: -
Model: gpt-oss-20b
Configuration
# LLM-Benchmark Konfiguration
# Modell : gpt-oss-20b
# Engine : vLLM
# Run-ID : run-20260724-082940-8305a5
# GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
# CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores
# RAM : 125 GB
bench@llm-benchmark:~$ /home/godcore/vllm-venv/bin/python3 /home/godcore/vllm-venv/bin/vllm serve openai/gpt-oss-20b \
--served-model-name gpt-oss-20b \
--tensor-parallel-size 1 \
--dtype auto \
--max-model-len 8192 \
--gpu-memory-utilization 0.90 \
--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 |
| Tensor-Parallel?Anzahl GPUs, auf die JEDER einzelne Modell-Layer aufgeteilt wird (Tensor-Parallelitaet). Mehr GPUs = mehr VRAM und meist mehr Speed, aber die Anzahl der Attention-Heads muss durch diesen Wert teilbar sein (z.B. 32 Heads -> nur 1, 2, 4, 8 ... moeglich, NICHT 3). | 1 |
| 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'. | 0.90 |
Anzeige
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/sNVIDIA GeForce RTX 5090 1.890,7 tok/s★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.835,7 tok/s this runNVIDIA 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/sTesla V100-PCIE-32GB 206,6 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/sAMD Ryzen 7 5800X3D 8-Core Processor 1.890,7 tok/s★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 1.835,7 tok/s this runAMD 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/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 206,6 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/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.890,7 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.835,7 tok/s this runASUSTeK 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. ROG STRIX X570-F GAMING 206,6 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
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 URLReset
⚡ Electricity price
EUR/kWh
⚙️ System utilization
100 %
🖥️ Acquisition
EUR
🔌 Idle
105 W
⚡ TDP
383 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)383 W estimated (TDP)GPU 300 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 0.13
Token / kWh2.38M
Acquisition (system)EUR 19,698 full priceGPU EUR 13,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 150
Electricity (2 years)–
TCO (2 years)EUR 21,708
Output tokens (2 years)15.94B
☁️ 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 (105 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 RTX PRO 6000 Blackwell Max-Q Workstation Edition | 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 RTX PRO 6000 Blackwell Max-Q Workstation Edition · this run 253 tok/sNVIDIA GeForce RTX 5090 405 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 395 tok/sNVIDIA 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.