ℹ

Public note: Dell PowerEdge R820 . 2x AMD Radeon RX 7900 XTX (48 GB VRAM gesamt, ROCm/HIP) . RAM: 32x 16 GB SK Hynix DDR3-1600 ECC RDIMM (HMT42GR7AFR4A-PB) = 512 GB @ 1600 MT/s

Generation185,17tok/s

Prefill2.485,70tok/s

Time to First Token4.503,00ms

Total duration70,73s

Concurrency5parallel

Ranking in the field

This GPU All GPUs

690of 1469 systems

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

This run is better than 53 % of all comparable systems.

Generation 185,2 tok/s

-25 % vs Ø 246,5

Prefill 2.485,7 tok/s

-54 % vs Ø 5.365,8

Time to First Token 4.503 ms

-85 % vs Ø 30.155

Distribution in the field0 – 1.349 tok/s

Ø 247 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 GeForce RTX 5090 · run-20260728-184455-5b4937

1.301,9 tok/s

gemma-4-E2B-it3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-4111a9

1.195,7 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 GeForce RTX 5090 · run-20260728-194135-5432cd

1.164,8 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

Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-b22926

1.135,0 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31

1.113,5 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91

1.090,6 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e

1.077,4 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818

1.071,0 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92

1.051,1 tok/s

gpt-oss-20b3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a

1.015,5 tok/s

Nemotron-3-Nano-30B-A3B this run2× 2x AMD Radeon RX 7900 XTX · run-20261009-081231-034a43

185,2 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-20260729-032121-305ad6

1.007,8 tok/s

NVIDIA GeForce RTX 5090run-20260729-105335-a19450

990,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-60b672

930,9 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-88bf57

929,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105340-3e284e

899,0 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-060802-676205

550,0 tok/s

2× NVIDIA RTX A6000run-20260827-221527-96e3ca

450,9 tok/s

2× NVIDIA RTX A6000run-20260830-051029-156991

448,7 tok/s

NVIDIA RTX A6000run-20260826-211812-3aa2ec

419,4 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-082937-f1f843

397,8 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260804-052131-5e919d

300,1 tok/s

NVIDIA RTX A6000run-20260827-013605-e50e29

254,4 tok/s

NVIDIA RTX A6000run-20260826-134908-7cdbb5

228,6 tok/s

2× NVIDIA RTX A6000run-20260827-154104-631de7

218,2 tok/s

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820

Setup

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

Configuration

benchmark-konfiguration — run-20261009-081231-034a43

# LLM-Benchmark Konfiguration # Modell : Nemotron-3-Nano-30B-A3B # Engine : llama.cpp # Run-ID : run-20261009-081231-034a43 # GPU : 2x AMD Radeon RX 7900 XTX # CPU : 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz # RAM : 504 GB bench@llm-benchmark:~$ llama-server \ -m nvidia_Nemotron-3-Nano-30B-A3B-IQ4_XS.gguf \ --alias NVIDIA-Nemotron-3-Nano-30B-A3B \ -ngl 999 \ -sm layer \ -fa on \ -c 40960 \ -np 10 '(2x' RX 7900 XTX ROCm/HIP, 'gpu)'

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.	NVIDIA-Nemotron-3-Nano-30B-A3B
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	40960
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	nvidia_Nemotron-3-Nano-30B-A3B-IQ4_XS.gguf
GPU-Layer?Anzahl der auf die GPU ausgelagerten Modell-Layer. Hoeher = mehr VRAM und schneller; der Rest laeuft auf der CPU. 999 = alles auf GPU.	999
Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise).	layer
fa	on
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	40960
np	10
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Nemotron-3-Nano-30B-A3B 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 1.773,5 tok/sNVIDIA GeForce RTX 5090 1.722,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.654,6 tok/sNVIDIA GeForce RTX 3090 Ti 897,5 tok/sNVIDIA RTX A6000 756,7 tok/sAMD Radeon AI PRO R9700 294,4 tok/sNVIDIA GeForce RTX 5070 Ti 263,3 tok/s★ AMD Radeon RX 7900 XTX 244,9 tok/s this runNVIDIA GB10 (DGX Spark) 58,3 tok/sNVIDIA GeForce RTX 2060 15,1 tok/sCPU-only 6,6 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.773,5 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.722,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.654,6 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 897,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 756,7 tok/sAMD Ryzen 5 5600X 6-Core Processor 404,7 tok/sAMD Ryzen 3 3100 4-Core Processor 294,4 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 263,3 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 244,9 tok/s this runNVIDIA Grace 58,3 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 6,6 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.773,5 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.722,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.654,6 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 897,5 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 404,7 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 294,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 263,3 tok/s★ Dell Inc. PowerEdge R820 244,9 tok/s this runASUSTeK COMPUTER INC. GX10 58,3 tok/s

ENGby engine

★ llama.cpp 1.773,5 tok/s this runvLLM 588,5 tok/sunbekannt 404,7 tok/s

DRVby driver

unbekannt 1.773,5 tok/sNVIDIA 590.48.01 / CUDA 13.1 58,3 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 35 W

⚡ TDP 749 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)749 W estimated (TDP)GPU 710 + CPU 29 + Board 10 W full load

Avg cost / hourEUR 0.22

Electricity / 1M tokensEUR 0.34

Token / kWh890.30K

Acquisition (system)EUR 4,353 partial priceGPU EUR 2,098 · CPU EUR 59 · RAM EUR 2,016 · PSU EUR 180

Electricity (2 years)–

TCO (2 years)EUR 8,288

Output tokens (2 years)11.68B

☁️ 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 (35 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-30B-A3B2x AMD Radeon RX 7900 XTX	Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090	Nemotron-3-Nano-30B-A3B3x 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)	–	–	–	–

2× AMD Radeon RX 7900 XTX · this run 185 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,008 tok/s NVIDIA GeForce RTX 5090 991 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.