Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaNVIDIA

Nemotron-Cascade-2-30B-A3B

Performance benchmark · measured on 28.07.2026 22:11

Benchmark-IDrun-20260729-032120-1b1a49
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
Generation1.768,14tok/s
Prefill8.360,06tok/s
Time to First Token6.952,00ms
Total duration38,62s
Concurrency10parallel
Ranking in the field
6of 61 systems

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

This run is better than 92 % of all comparable systems.
Generation 1.768,1 tok/s
+74 % vs Ø 1.019,1
Prefill 8.360,1 tok/s
-25 % vs Ø 11.171,0
Time to First Token 6.952 ms
-71 % vs Ø 24.203
Distribution in the field0 – 2.414 tok/s
Ø 1.019 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-b37ed9
2.414,4 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-311459
1.791,5 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-e2403f
1.773,5 tok/s
Nemotron-Cascade-2-30B-A3B this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032120-1b1a49
1.768,1 tok/s
gemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-866815
1.758,6 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-9f055e
1.757,4 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-f34b37
1.753,8 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-1e8c74
1.740,4 tok/s
Mamba-Codestral-7B-v0.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-194136-5b0cb8
1.712,6 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032124-ef2bb1
1.690,0 tok/s
Qwen3-30B-A3B-Thinking-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032123-88fa84
1.670,5 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032122-3d6d17
1.658,1 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 10× concurrent · Generation (tok/s)

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen 9 9950X 16-Core Processor
RAM: 92 GB
Mainboard: ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Nemotron-Cascade-2-30B-A3B

Configuration

benchmark-konfiguration — run-20260729-032120-1b1a49
# LLM-Benchmark Konfiguration # Modell : Nemotron-Cascade-2-30B-A3B # Engine : llama.cpp # Run-ID : run-20260729-032120-1b1a49 # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : AMD Ryzen 9 9950X 16-Core Processor # RAM : 92 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
np4

All benchmarks of this model To leaderboard

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

2.2971.7231.1495740,002.8155.6298.444Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 270,4 tok/s Generation, 4.693 tok/s Prefill, TTFT 3.298 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 262,4 tok/s Generation, 720 tok/s Prefill, TTFT 26.930 ms (3 Laufe)NVIDIA GeForce RTX 50...AMD Radeon 8060S Graphics - 114,5 tok/s Generation, 1.028 tok/s Prefill, TTFT 5.654 ms (2 Laufe)AMD Radeon 8060S Grap...CPU-only - 5,9 tok/s Generation, 72 tok/s Prefill, TTFT 130.288 ms (3 Laufe)CPU-onlyNVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.768,1 tok/s Generation, 6.820 tok/s Prefill, TTFT 3.302 ms (3 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.768,1 tok/s this runAMD 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

2.2971.7231.1495740,002.8155.6298.444Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 270,4 tok/s Generation, 4.693 tok/s Prefill, TTFT 3.298 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 262,4 tok/s Generation, 720 tok/s Prefill, TTFT 26.930 ms (3 Laufe)AMD Ryzen Threadrippe...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 114,5 tok/s Generation, 1.028 tok/s Prefill, TTFT 5.654 ms (2 Laufe)AMD RYZEN AI MAX+ 395...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 5,9 tok/s Generation, 72 tok/s Prefill, TTFT 130.288 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen 9 9950X 16-Core Processor - 1.768,1 tok/s Generation, 6.820 tok/s Prefill, TTFT 3.302 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 9950X 16-...
★ AMD Ryzen 9 9950X 16-Core Processor 1.768,1 tok/s this runAMD 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

2.2971.7231.1495740,002.8155.6298.444Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 270,4 tok/s Generation, 4.693 tok/s Prefill, TTFT 3.298 ms (2 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 262,4 tok/s Generation, 720 tok/s Prefill, TTFT 26.930 ms (3 Laufe)ASUSTeK COMPUTER INC....Bosgame AXB35-02 (BeyondMax Series) - 114,5 tok/s Generation, 1.028 tok/s Prefill, TTFT 5.654 ms (2 Laufe)Bosgame AXB35-02 (Bey...Dell Inc. PowerEdge R820 - 5,9 tok/s Generation, 72 tok/s Prefill, TTFT 130.288 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.768,1 tok/s Generation, 6.820 tok/s Prefill, TTFT 3.302 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.768,1 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 270,4 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

1.9451.8571.7681.6801.5912.4792.5842.6902.795Prefill (tok/s)Generation (tok/s)llama.cpp - 1.768,1 tok/s Generation, 2.637 tok/s Prefill, TTFT 38.420 ms (13 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.768,1 tok/s this run

DRVby driver

1.9451.8571.7681.6801.5912.4792.5842.6902.795Prefill (tok/s)Generation (tok/s)unbekannt - 1.768,1 tok/s Generation, 2.637 tok/s Prefill, TTFT 38.420 ms (13 Laufe)unbekannt
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 URLReset
⚡ Electricity price EUR/kWh
⚙️ System utilization 100 %
🖥️ Acquisition EUR
🔌 Idle 70 W
⚡ TDP 644 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)644 W estimated (TDP)GPU 600 + CPU 29 + Board 15 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 0.030
Token / kWh9.89M
Acquisition (system)EUR 15,248 full priceGPU EUR 13,000 · CPU EUR 649 · Board EUR 499 · RAM EUR 920 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 18,632
Output tokens (2 years)111.52B
☁️ 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 (70 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-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionNemotron-Cascade-2-30B-A3B3x AMD Radeon AI PRO R9700Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5070 TiNemotron-Cascade-2-30B-A3BKeine GPU (CPU-only)
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)

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.