# LLM-Benchmark Konfiguration # Modell : Nemotron-3-Nano-4B # Engine : llama.cpp # Run-ID : run-20260722-194041-46cba2 # GPU : 2x NVIDIA GeForce RTX 2060 # CPU : 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz # RAM : 504 GB bench@llm-benchmark:~$ /opt/llama.cpp/build/bin/llama-server \ -m /opt/models/NVIDIA-Nemotron-3-Nano-4B-Q4_K_M.gguf \ -a NVIDIA-Nemotron-3-Nano-4B \ --host 0.0.0.0 \ --port 8080 \ --numa distribute \ -t 64 \ -tb 64 \ -c 8192 \ --parallel 4

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-4B
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	8192
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	/opt/models/NVIDIA-Nemotron-3-Nano-4B-Q4_K_M.gguf
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.	NVIDIA-Nemotron-3-Nano-4B
NUMA?NUMA-Optimierung fuer Multi-Socket-CPUs: distribute/isolate/numactl. Verbessert die Speicherlokalitaet.	distribute
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).	64
Batch-Threads?Anzahl CPU-Threads fuer Prompt-Verarbeitung und Batch (Prefill).	64
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	8192
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.	4

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/sNVIDIA 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/s★ NVIDIA GeForce RTX 2060 125,7 tok/s this run

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 2.182,7 tok/sAMD 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/sIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz 125,7 tok/s★ Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 8,0 tok/s this run

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 2.182,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.937,7 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.878,7 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/sASRock H110 Pro BTC+ 125,7 tok/s★ Dell Inc. PowerEdge R820 8,0 tok/s this run

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 (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 55 W

⚡ TDP 359 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)359 W estimated (TDP)GPU 320 + CPU 29 + Board 10 W full load

Avg cost / hourEUR 0.11

Electricity / 1M tokensEUR 6.05

Token / kWh49.57K

Acquisition (system)EUR 2,425 partial priceGPU EUR 220 · CPU EUR 39 · RAM EUR 2,016 · PSU EUR 150

Electricity (2 years)–

TCO (2 years)EUR 4,311

Output tokens (2 years)311.58M

☁️ 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 (55 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-4B2x NVIDIA GeForce RTX 2060	Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090	Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell 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)	–	–	–	–

2× NVIDIA GeForce RTX 2060 · this run 5 tok/s NVIDIA GeForce RTX 5090 394 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 393 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 362 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.