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

Nemotron-Cascade-2-30B-A3B

Performance benchmark · measured on 29.07.2026 04:08

Benchmark-IDrun-20260729-060802-b93c1e
Timebench 3 - Kombi (Prefill + Generation)MoE30BRuntime: llama.cppQuantisierung: Q4_K_M
Generation897,47tok/s
Prefill4.559,75tok/s
Time to First Token13.828,50ms
Total duration76,39s
Concurrency10parallel
Ranking in the field
117of 346 systems

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

This run is better than 66 % of all comparable systems.
Generation 897,5 tok/s
+38 % vs Ø 651,3
Prefill 4.559,8 tok/s
-31 % vs Ø 6.626,4
Time to First Token 13.829 ms
-67 % vs Ø 41.299
Distribution in the field0 – 2.491 tok/s
Ø 651 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e28775
2.491,2 tok/s
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
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-e0eafd
1.897,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-7c961d
1.890,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd
1.878,7 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b
1.835,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046
1.830,3 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-c6e7e0
1.819,5 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-2b99aa
1.802,0 tok/s
Nemotron-Cascade-2-30B-A3B this runNVIDIA GeForce RTX 3090 Ti · run-20260729-060802-b93c1e
897,5 tok/s

How does this benchmark compare on other GPUs?

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

Configuration

benchmark-konfiguration — run-20260729-060802-b93c1e
# LLM-Benchmark Konfiguration # Modell : Nemotron-Cascade-2-30B-A3B # Engine : llama.cpp # Run-ID : run-20260729-060802-b93c1e # 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--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./root/.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)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.768,1 tok/s Generation, 6.820 tok/s Prefill, TTFT 3.302 ms (3 Laufe)NVIDIA RTX PRO 6000 B...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 GeForce RTX 3090 Ti - 897,5 tok/s Generation, 3.962 tok/s Prefill, TTFT 6.439 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 30...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.768,1 tok/s★ NVIDIA GeForce RTX 3090 Ti 897,5 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 9 9950X 16-Core Processor - 1.768,1 tok/s Generation, 6.820 tok/s Prefill, TTFT 3.302 ms (3 Laufe)AMD Ryzen 9 9950X 16-...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 8945HX with Radeon Graphics - 897,5 tok/s Generation, 3.962 tok/s Prefill, TTFT 6.439 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 8945HX wi...
AMD Ryzen 9 9950X 16-Core Processor 1.768,1 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 897,5 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. ProArt X870E-CREATOR WIFI - 1.768,1 tok/s Generation, 6.820 tok/s Prefill, TTFT 3.302 ms (3 Laufe)ASUSTeK COMPUTER INC....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...Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 897,5 tok/s Generation, 3.962 tok/s Prefill, TTFT 6.439 ms (3 Laufe) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.768,1 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 897,5 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

1.9451.8571.7681.6801.5912.7122.8282.9433.058Prefill (tok/s)Generation (tok/s)llama.cpp - 1.768,1 tok/s Generation, 2.885 tok/s Prefill, TTFT 32.424 ms (16 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.768,1 tok/s this run

DRVby driver

1.9451.8571.7681.6801.5912.7122.8282.9433.058Prefill (tok/s)Generation (tok/s)unbekannt - 1.768,1 tok/s Generation, 2.885 tok/s Prefill, TTFT 32.424 ms (16 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 50 W
⚡ TDP 477 W
☁️ External LLM (API)
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 0.044
Token / kWh6.77M
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)56.61B
☁️ 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

Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 3090 TiNemotron-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 Ti
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.