Contributed byMario AlkaNVIDIA Nemotron-Cascade-2-30B-A3B
Performance benchmark · measured on 23.07.2026 00:55
Benchmark-ID
run-20260723-015520-d2cd35Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
Generation5,86tok/s
Prefill61,21tok/s
Time to First Token35.481,00ms
Total duration420,63s
Concurrency1parallel
Ranking in the field
1348of 1549 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent
This run is better than 13 % of all comparable systems.
Generation
5,9 tok/s
-93 % vs Ø 79,0
Prefill
61,2 tok/s
-98 % vs Ø 2.837,1
Time to First Token
35.481 ms
+32 % vs Ø 26.963
Distribution in the field0 – 405 tok/s
Wie schlägt sich dieser Benchmark mit anderen Modellen?
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004608-16af9b
404,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9f766a
395,2 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7
393,5 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11
393,5 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004607-29bd16
388,9 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-1c779f
388,2 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089
378,6 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e8b129
377,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105335-653788
359,4 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090 · run-20260729-105334-2c4905
359,3 tok/s
Nemotron-Cascade-2-30B-A3B same modelNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7
359,0 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf
357,1 tok/s
Nemotron-Cascade-2-30B-A3B this run2× NVIDIA GeForce RTX 2060 · run-20260723-015520-d2cd35
5,9 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 1× concurrent · Generation (tok/s)
NVIDIA GeForce RTX 5090run-20260729-105334-44d1e7
359,0 tok/s
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032120-4e3476
356,8 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105340-3ddb51
330,2 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105340-508364
329,9 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105340-f538c5
327,7 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260729-060801-1e5cba
221,8 tok/s
NVIDIA RTX A6000run-20260826-211811-bea37a
180,6 tok/s
2× NVIDIA RTX A6000run-20260830-051029-ad38a6
171,1 tok/s
2× NVIDIA RTX A6000run-20260828-101910-9d02d3
170,8 tok/s
NVIDIA RTX A6000run-20260826-062050-97df90
157,0 tok/s
2× NVIDIA RTX A6000run-20260828-080811-e4d27f
145,4 tok/s
2× NVIDIA RTX A6000run-20260829-212822-9711b8
145,2 tok/s
NVIDIA GeForce RTX 5070 Tirun-20260818-080548-cee82f
138,8 tok/s
NVIDIA RTX A6000run-20260826-131708-543512
131,8 tok/s
Hardware
GPU: 2x NVIDIA GeForce RTX 2060 · 6 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820
Setup
Runtime: llama.cpp
Quantization: Q4_K_M
Model: Nemotron-Cascade-2-30B-A3B
Configuration
# LLM-Benchmark Konfiguration
# Modell : Nemotron-Cascade-2-30B-A3B
# Engine : llama.cpp
# Run-ID : run-20260723-015520-d2cd35
# 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/Nemotron-Cascade-2-30B-A3B-Q4_K_M.gguf \
-a Nemotron-Cascade-2-30B-A3B \
--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. | Nemotron-Cascade-2-30B-A3B |
| 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/Nemotron-Cascade-2-30B-A3B-Q4_K_M.gguf |
| Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen. | Nemotron-Cascade-2-30B-A3B |
| 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 |
Anzeige
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/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.655,2 tok/sNVIDIA GeForce RTX 3090 Ti 897,5 tok/sNVIDIA RTX A6000 723,7 tok/sAMD Radeon 8060S Graphics 326,9 tok/sNVIDIA GeForce RTX 5070 Ti 262,4 tok/sNVIDIA GB10 (DGX Spark) 148,8 tok/sAMD Radeon AI PRO R9700 122,1 tok/s★ NVIDIA GeForce RTX 2060 5,9 tok/s this run
CPUby processor
AMD Ryzen 9 9950X 16-Core Processor 1.768,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.719,2 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.655,2 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 897,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 723,7 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 326,9 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 262,4 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 219,6 tok/sNVIDIA Grace 148,8 tok/s★ Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 5,9 tok/s this run
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/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.655,2 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 897,5 tok/sBosgame AXB35-02 (BeyondMax Series) 326,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 262,4 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 219,6 tok/sASUSTeK COMPUTER INC. GX10 148,8 tok/s★ Dell Inc. PowerEdge R820 5,9 tok/s this run
DRVby driver
unbekannt 1.768,1 tok/sNVIDIA 590.48.01 / CUDA 13.1 148,8 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 URLReset
⚡ Electricity price
EUR/kWh
⚙️ System utilization
100 %
🖥️ Acquisition
EUR
🔌 Idle
55 W
⚡ TDP
359 W
☁️ External LLM (API)
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 5.10
Token / kWh58.80K
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)369.60M
☁️ 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-Cascade-2-30B-A3B2x NVIDIA GeForce RTX 2060 | Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090 | Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition | 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) | – | – | – | – |
2× NVIDIA GeForce RTX 2060 · this run 6 tok/sNVIDIA GeForce RTX 5090 359 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 357 tok/s3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 330 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.