ℹ

Public note: Rechnerische Variante: Messwerte der NVIDIA RTX PRO 6000 Blackwell Workstation Edition (gemessen auf godcore-ai-002) uebertragen auf die Host-Konfiguration von godcore-worker-004 (AMD Ryzen 5 5600X, 32 GB RAM). Keine eigene Messung dieser Kombination. Quelle: run-20260729-032119-1ddf01 (2026-07-28 21:04:55).

Generation985,75tok/s

Prefill7.733,44tok/s

Time to First Token2.448,00ms

Total duration20,88s

Concurrency5parallel

Ranking in the field

This GPU All GPUs

13of 104 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 88 % of all comparable systems.

Generation 985,8 tok/s

+65 % vs Ø 599,1

Prefill 7.733,4 tok/s

-6 % vs Ø 8.234,0

Time to First Token 2.448 ms

-90 % vs Ø 25.079

Distribution in the field0 – 1.349 tok/s

Ø 599 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d

1.349,3 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071844-e5e309

1.348,4 tok/s

Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864

1.188,7 tok/s

Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071851-c3c4a5

1.154,4 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9

1.136,3 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-09627f

1.135,0 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071836-99dfa5

1.105,8 tok/s

Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6

1.007,8 tok/s

Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032120-4b8514

1.007,3 tok/s

Nemotron-3-Nano-Omni-30B-A3B-Reasoning same modelNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-1ddf01

1.007,0 tok/s

Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071924-ea006b

1.005,7 tok/s

Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071931-9d8567

997,7 tok/s

Nemotron-3-Nano-Omni-30B-A3B-Reasoning this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071938-51f264

985,8 tok/s

Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-17e7b6

975,1 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× concurrent · Generation (tok/s)

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032119-1ddf01

1.007,0 tok/s

NVIDIA GeForce RTX 5090run-20260729-105334-daa9ee

992,1 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Edition this runrun-20261023-071938-51f264

985,8 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105340-c65107

931,3 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105340-030105

925,4 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-8989eb

896,4 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-035835-01ffd0

547,9 tok/s

NVIDIA RTX A6000run-20260826-225451-1c46e6

348,2 tok/s

2× NVIDIA RTX A6000run-20260827-024202-d0d28e

264,7 tok/s

2× NVIDIA RTX A6000run-20260830-015225-879516

246,7 tok/s

2× NVIDIA RTX A6000run-20260828-084107-2f8a7e

245,2 tok/s

2× NVIDIA RTX A6000run-20260828-073525-9c7677

218,3 tok/s

2× NVIDIA RTX A6000run-20260829-212822-152ce0

217,4 tok/s

NVIDIA RTX A6000run-20260826-131708-629830

201,0 tok/s

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen 5 5600X 6-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Nemotron-3-Nano-Omni-30B-A3B-Reasoning

Configuration

benchmark-konfiguration — run-20261023-071938-51f264

# LLM-Benchmark Konfiguration # Modell : Nemotron-3-Nano-Omni-30B-A3B-Reasoning # Engine : llama.cpp # Run-ID : run-20261023-071938-51f264 # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : AMD Ryzen 5 5600X 6-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/.cache/huggingface/hub/models--DevQuasar--nvidia.Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16-GGUF/snapshots/7131823f6f6ffda04b65763677f2f1dbe15eb3c5/nvidia.Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16.f16.gguf.Q4_K_M.gguf \ -c 16384 \ -np 12

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.	llamacpp
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.	Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	/home/godcore/.cache/huggingface/hub/models--DevQuasar--nvidia.Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16-GGUF/snapshots/7131823f6f6ffda04b65763677f2f1dbe15eb3c5/nvidia.Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16.f16.gguf.Q4_K_M.gguf
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	16384
np	12
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Nemotron-3-Nano-Omni-30B-A3B-Reasoning 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 1.791,5 tok/s this runNVIDIA GeForce RTX 5090 1.706,7 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.651,0 tok/sNVIDIA GeForce RTX 3090 Ti 896,6 tok/sNVIDIA RTX A6000 527,0 tok/sNVIDIA GeForce RTX 5070 Ti 262,5 tok/sAMD Radeon AI PRO R9700 122,4 tok/sAMD Radeon RX 7900 XTX 76,7 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.791,5 tok/s★ AMD Ryzen 5 5600X 6-Core Processor 1.774,4 tok/s this runAMD Ryzen 7 5800X3D 8-Core Processor 1.706,7 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.651,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 896,6 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 527,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 262,5 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 76,7 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.791,5 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.774,4 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.651,0 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 896,6 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 262,5 tok/sDell Inc. PowerEdge R820 76,7 tok/s

ENGby engine

★ llama.cpp 1.791,5 tok/s this runvLLM 527,0 tok/s

DRVby driver

unbekannt 1.791,5 tok/s

💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (5× 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 42 W

⚡ TDP 612 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)612 W estimated (TDP)GPU 600 + Board 12 W full load

Avg cost / hourEUR 0.18

Electricity / 1M tokensEUR 0.052

Token / kWh5.80M

Acquisition (system)EUR 13,698 full priceGPU EUR 13,000 · CPU EUR 121 · Board EUR 149 · RAM EUR 248 · PSU EUR 180

Electricity (2 years)–

TCO (2 years)EUR 16,915

Output tokens (2 years)62.17B

☁️ 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 (42 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

	Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090	Nemotron-3-Nano-Omni-30B-A3B-Reasoning3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
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 Workstation Edition · this run 986 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,007 tok/s NVIDIA GeForce RTX 5090 992 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 931 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.