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

Generation108,28tok/s

Prefill1.035,62tok/s

Time to First Token25.801,00ms

Total duration242,45s

Concurrency10parallel

Ranking in the field

This GPU All GPUs

1071of 1427 systems

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

This run is better than 25 % of all comparable systems.

Generation 108,3 tok/s

-75 % vs Ø 425,3

Prefill 1.035,6 tok/s

-84 % vs Ø 6.659,3

Time to First Token 25.801 ms

-44 % vs Ø 45.848

Distribution in the field0 – 2.491 tok/s

Ø 425 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

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

2.263,7 tok/s

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

2.182,7 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

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86

1.937,7 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa

1.911,6 tok/s

Nemotron-3-Nano-4B3× 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

Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd

1.878,7 tok/s

gpt-oss-20b3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b

1.835,7 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046

1.830,3 tok/s

Llama-3.3-Nemotron-Super-49B-v1.5 this run2× 2x AMD Radeon RX 7900 XTX · run-20261009-081233-72d841

108,3 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-20260729-032132-7e4eca

364,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260731-071559-4b3ef7

303,0 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260731-071559-f8cf32

291,2 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260731-071559-846bfa

249,3 tok/s

2× NVIDIA RTX A6000run-20260830-033127-b7ca45

197,3 tok/s

2× NVIDIA RTX A6000run-20260827-203813-b4c679

183,5 tok/s

2× NVIDIA RTX A6000run-20260828-020607-970912

154,0 tok/s

2× NVIDIA RTX A6000run-20260830-093432-76b060

153,6 tok/s

2× AMD Radeon RX 7900 XTX this runrun-20261009-081233-72d841

108,3 tok/s

AMD Radeon PRO W7900 Dual Slotrun-20260817-153343-c38135

71,0 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260729-105334-640dbf

25,2 tok/s

NVIDIA GeForce RTX 5090run-20260731-071559-2ee795

20,2 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-122848-a31762

19,6 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053413-3ffb32

11,4 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: Llama-3.3-Nemotron-Super-49B-v1.5

Configuration

benchmark-konfiguration — run-20261009-081233-72d841

# LLM-Benchmark Konfiguration # Modell : Llama-3.3-Nemotron-Super-49B-v1.5 # Engine : llama.cpp # Run-ID : run-20261009-081233-72d841 # 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_Llama-3_3-Nemotron-Super-49B-v1_5-IQ4_XS.gguf \ --alias Llama-3_3-Nemotron-Super-49B-v1_5 \ -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.	Llama-3_3-Nemotron-Super-49B-v1_5
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_Llama-3_3-Nemotron-Super-49B-v1_5-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

Llama-3.3-Nemotron-Super-49B-v1.5 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 364,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 303,0 tok/sNVIDIA RTX A6000 197,3 tok/s★ AMD Radeon RX 7900 XTX 108,3 tok/s this runAMD Radeon PRO W7900 Dual Slot 71,0 tok/sNVIDIA GeForce RTX 5070 Ti 25,2 tok/sNVIDIA GeForce RTX 5090 20,2 tok/sNVIDIA GeForce RTX 3090 Ti 19,6 tok/sAMD Radeon AI PRO R9700 11,6 tok/sNVIDIA GeForce RTX 2060 1,1 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 364,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 303,0 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 197,3 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 108,3 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 71,0 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 20,2 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,6 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 364,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 303,0 tok/s★ Dell Inc. PowerEdge R820 108,3 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 71,0 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 20,2 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 19,6 tok/s

ENGby engine

★ llama.cpp 364,1 tok/s this runvLLM 197,3 tok/s

DRVby driver

unbekannt 364,1 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 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 0.58

Token / kWh520.61K

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)6.83B

☁️ 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

	Llama-3.3-Nemotron-Super-49B-v1.52x AMD Radeon RX 7900 XTX	Llama-3.3-Nemotron-Super-49B-v1.5NVIDIA RTX PRO 6000 Blackwell Workstation Edition	Llama-3.3-Nemotron-Super-49B-v1.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Llama-3.3-Nemotron-Super-49B-v1.53x 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 108 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 364 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 303 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 291 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.