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-20260727-181607-4cca42 (2026-07-27 18:12:21).

Generation2.144,30tok/s

Prefill10.532,84tok/s

Time to First Token5.598,00ms

Total duration31,57s

Concurrency10parallel

Ranking in the field

This GPU All GPUs

6of 1459 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 10× concurrent

This run is better than 100 % of all comparable systems.

Generation 2.144,3 tok/s

+379 % vs Ø 447,4

Prefill 10.532,8 tok/s

+54 % vs Ø 6.827,2

Time to First Token 5.598 ms

-88 % vs Ø 44.979

Distribution in the field0 – 2.491 tok/s

Ø 447 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e28775

2.491,2 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-b37ed9

2.414,4 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065752-48370d

2.412,3 tok/s

Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-dce558

2.263,7 tok/s

Nemotron-3-Nano-4B same modelNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42

2.182,7 tok/s

Nemotron-3-Nano-4B this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065758-96fe6a

2.144,3 tok/s

gemma-4-E2B-it3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73

2.143,6 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9c966e

1.995,4 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4

1.993,5 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065808-332d1f

1.981,1 tok/s

Nemotron-3-Nano-4B same model3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86

1.937,7 tok/s

Nemotron-3-Nano-4B same model3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa

1.911,6 tok/s

Nemotron-3-Nano-4B same model3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-e0eafd

1.897,0 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-7c961d

1.890,7 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 10× concurrent · Generation (tok/s)

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260727-181607-4cca42

2.182,7 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Edition this runrun-20261023-065758-96fe6a

2.144,3 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-194136-0aed86

1.937,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-194136-8db0fa

1.911,6 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260727-181606-e0eafd

1.897,0 tok/s

NVIDIA GeForce RTX 5090run-20260728-194135-2ed9dd

1.878,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-194136-a77046

1.830,3 tok/s

2× NVIDIA RTX A6000run-20260829-095458-12e451

1.485,1 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-090153-f232e7

1.197,0 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260727-145956-3936c2

992,1 tok/s

NVIDIA RTX A6000run-20260826-194154-9b98f6

791,5 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053357-052e4d

667,0 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053357-4f0c35

655,3 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053357-057013

629,4 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-4B

Configuration

benchmark-konfiguration — run-20261023-065758-96fe6a

# LLM-Benchmark Konfiguration # Modell : Nemotron-3-Nano-4B # Engine : llama.cpp # Run-ID : run-20261023-065758-96fe6a # 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.NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/snapshots/86e3ddc0b34d94852cae725ade1b9b015b516f38/nvidia.NVIDIA-Nemotron-3-Nano-4B-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-4B
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.NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF/snapshots/86e3ddc0b34d94852cae725ade1b9b015b516f38/nvidia.NVIDIA-Nemotron-3-Nano-4B-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-4B 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 2.182,7 tok/s this runNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.937,7 tok/sNVIDIA GeForce RTX 5090 1.878,7 tok/sNVIDIA RTX A6000 1.485,1 tok/sNVIDIA GeForce RTX 5070 Ti 1.197,0 tok/sNVIDIA GeForce RTX 3090 Ti 992,1 tok/sAMD Radeon AI PRO R9700 667,0 tok/sNVIDIA GB10 (DGX Spark) 367,8 tok/sNVIDIA GeForce RTX 2060 125,7 tok/sCPU-only 8,0 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 2.182,7 tok/s★ AMD Ryzen 5 5600X 6-Core Processor 2.144,3 tok/s this runAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.937,7 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.878,7 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 1.485,1 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 1.197,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 992,1 tok/sNVIDIA Grace 367,8 tok/sAMD Ryzen 3 3100 4-Core Processor 344,9 tok/sIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz 125,7 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 8,0 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 2.182,7 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 2.144,3 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.937,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1.197,0 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 992,1 tok/sASUSTeK COMPUTER INC. GX10 367,8 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 344,9 tok/sASRock H110 Pro BTC+ 125,7 tok/sDell Inc. PowerEdge R820 8,0 tok/s

ENGby engine

★ llama.cpp 2.182,7 tok/s this runvLLM 1.485,1 tok/s

DRVby driver

unbekannt 2.182,7 tok/sNVIDIA 590.48.01 / CUDA 13.1 367,8 tok/s

💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× 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 0.024

Token / kWh12.61M

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)135.25B

☁️ 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-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Nemotron-3-Nano-4B3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Nemotron-3-Nano-4B3x 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 2,144 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 2,183 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,938 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,912 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.