# LLM-Benchmark Konfiguration # Modell : Llama-3.3-Nemotron-Super-49B-v1.5 # Engine : llama.cpp # Run-ID : run-20260729-122848-5e237b # GPU : NVIDIA GeForce RTX 3090 Ti # CPU : AMD Ryzen 9 8945HX with Radeon Graphics # RAM : 92 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--gabriellarson--Llama-3_3-Nemotron-Super-49B-v1_5-GGUF/snapshots/c324e134daf0a0d4f9e3e136ae525df9fdebea3b/Llama-3_3-Nemotron-Super-49B-v1_5-Q4_K_M.gguf \ --alias Llama-3_3-Nemotron-Super-49B-v1_5 \ --host 0.0.0.0 \ --port 8000 \ -ngl 60 \ -c 16384 \ -np 4 \ --jinja

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.	16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	/root/.cache/huggingface/hub/models--gabriellarson--Llama-3_3-Nemotron-Super-49B-v1_5-GGUF/snapshots/c324e134daf0a0d4f9e3e136ae525df9fdebea3b/Llama-3_3-Nemotron-Super-49B-v1_5-Q4_K_M.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.	60
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	16384
np	4

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/sAMD Radeon PRO W7900 Dual Slot 71,0 tok/sNVIDIA GeForce RTX 5070 Ti 25,2 tok/sNVIDIA GeForce RTX 5090 20,2 tok/s★ NVIDIA GeForce RTX 3090 Ti 19,6 tok/s this runAMD Radeon AI PRO R9700 11,6 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/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 71,0 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 20,2 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 19,6 tok/s this run

MBby mainboard

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

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 (1× 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 50 W

⚡ TDP 477 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)477 W estimated (TDP)GPU 450 + CPU 17 + Board 10 W full load

Avg cost / hourEUR 0.14

Electricity / 1M tokensEUR 8.63

Token / kWh34.77K

Acquisition (system)EUR 2,986 partial priceGPU EUR 999 · CPU EUR 549 · RAM EUR 1,288 · PSU EUR 150

Electricity (2 years)–

TCO (2 years)EUR 5,494

Output tokens (2 years)290.76M

☁️ 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 (50 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-v1.5NVIDIA GeForce RTX 3090 Ti	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)	–	–	–	–

NVIDIA GeForce RTX 3090 Ti · this run 5 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 48 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 45 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 39 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.