# LLM-Benchmark Konfiguration # Modell : Nemotron-Cascade-2-30B-A3B # Engine : llama.cpp # Run-ID : run-20260729-105340-3fa079 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--mradermacher--Nemotron-Cascade-2-30B-A3B-GGUF/snapshots/d27b10b50877cdb55c38deb5e0f4d7eb6c55f6cc/Nemotron-Cascade-2-30B-A3B.Q4_K_M.gguf \ --alias Nemotron-Cascade-2-30B-A3B \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -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.	Nemotron-Cascade-2-30B-A3B
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--mradermacher--Nemotron-Cascade-2-30B-A3B-GGUF/snapshots/d27b10b50877cdb55c38deb5e0f4d7eb6c55f6cc/Nemotron-Cascade-2-30B-A3B.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.	999
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

Nemotron-Cascade-2-30B-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 1.768,1 tok/sNVIDIA GeForce RTX 5090 1.719,2 tok/s★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.655,2 tok/s this runNVIDIA GeForce RTX 3090 Ti 897,5 tok/sAMD Radeon AI PRO R9700 270,4 tok/sNVIDIA GeForce RTX 5070 Ti 262,4 tok/sAMD Radeon 8060S Graphics 114,5 tok/sCPU-only 5,9 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.768,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.719,2 tok/s★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 1.655,2 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 897,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 270,4 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 262,4 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 114,5 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 5,9 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.768,1 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.719,2 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.655,2 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 897,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 262,4 tok/sBosgame AXB35-02 (BeyondMax Series) 114,5 tok/sDell Inc. PowerEdge R820 5,9 tok/s

ENGby engine

★ llama.cpp 1.768,1 tok/s this run

DRVby driver

unbekannt 1.768,1 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 165 W

⚡ TDP 983 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load

Avg cost / hourEUR 0.29

Electricity / 1M tokensEUR 0.049

Token / kWh6.06M

Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200

Electricity (2 years)–

TCO (2 years)EUR 50,912

Output tokens (2 years)104.40B

☁️ 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 (165 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-Cascade-2-30B-A3B3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090	Nemotron-Cascade-2-30B-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)	–	–	–	–

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · this run 1,655 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,768 tok/s NVIDIA GeForce RTX 5090 1,719 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,651 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.