Created bymario-alka.dePowered bynoob2claw.detricoma.de
Contributed byMario AlkaNVIDIA

NVIDIA-Nemotron-3.5-Lightning-30B-A3B

Performance benchmark · measured on 22.09.2026 13:56

Benchmark-IDrun-20260922-123035-885adf
Timebench 3 - Kombi (Prefill + Generation)MoE31.6BRuntime: llama.cppQuantisierung: Q4_K_M
Generation112,45tok/s
Prefill2.606,90tok/s
Time to First Token827,00ms
Total duration19,87s
Concurrency1parallel
Ranking in the field
449of 1851 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 76 % of all comparable systems.
Generation 112,5 tok/s
+44 % vs Ø 77,9
Prefill 2.606,9 tok/s
-8 % vs Ø 2.847,6
Time to First Token 827 ms
-97 % vs Ø 24.622
Distribution in the field0 – 471 tok/s
Ø 78 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

NVIDIA-Nemotron-3.5-Lightning-30B-A3B same modelNVIDIA GeForce RTX 3090 · run-20261026-183943-a8c4f8
471,3 tok/s
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
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7
393,5 tok/s
NVIDIA-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
NVIDIA-Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
NVIDIA-Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
NVIDIA-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-A3BNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7
359,0 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3B this runAMD Radeon AI PRO R9700 · run-20260922-123035-885adf
112,5 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× concurrent · Generation (tok/s)

Hardware

GPU: AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen 3 3100 4-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: NVIDIA-Nemotron-3.5-Lightning-30B-A3B

Configuration

benchmark-konfiguration — run-20260922-123035-885adf
# LLM-Benchmark Konfiguration # Modell : NVIDIA-Nemotron-3.5-Lightning-30B-A3B # Engine : llama.cpp # Run-ID : run-20260922-123035-885adf # GPU : AMD Radeon AI PRO R9700 # CPU : AMD Ryzen 3 3100 4-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/models/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-Q4_K_M.gguf \ --alias NVIDIA-Nemotron-3.5-Lightning-30B-A3B \ -ngl 999 \ -fa on \ -c 40960 \ -np 10 '(AMD' Radeon AI PRO R9700, ROCm 7.2.4, 'HIP_VISIBLE_DEVICES=0)'
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-3.5-Lightning-30B-A3B
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.40960
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/models/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-UD-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
faon
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.40960
np10
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Videoreihe und Benchmarkauswertung zur AMD R9700
Model comparison

NVIDIA-Nemotron-3.5-Lightning-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

4.5023.3772.2511.1260,02213.3866.5529.718Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 3090 - 3.484,3 tok/s Generation, 7.781 tok/s Prefill, TTFT 4.659 ms (17 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 3090 Ti - 2.263,7 tok/s Generation, 8.103 tok/s Prefill, TTFT 10.659 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX SPARK (N1X) - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe)NVIDIA RTX SPARK (N1X)NVIDIA DGX SPARK (GB10) - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)NVIDIA DGX SPARK (GB1...AMD Radeon AI PRO R9700 - 290,3 tok/s Generation, 6.285 tok/s Prefill, TTFT 963 ms (30 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
NVIDIA GeForce RTX 3090 3.484,3 tok/sNVIDIA GeForce RTX 3090 Ti 2.263,7 tok/s★ AMD Radeon AI PRO R9700 290,3 tok/s this runNVIDIA RTX SPARK (N1X) 146,9 tok/sNVIDIA DGX SPARK (GB10) 136,6 tok/s

CPUby processor

4.5023.3772.2511.1260,02853.3186.3519.384Prefill (tok/s)Generation (tok/s)AMD Ryzen 5 5600X 6-Core Processor - 3.484,3 tok/s Generation, 7.834 tok/s Prefill, TTFT 5.559 ms (20 Laufe)AMD Ryzen 5 5600X 6-C...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe)AMD Ryzen Threadrippe...NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe)NVIDIA RTX Spark N1X ...NVIDIA Grace - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)NVIDIA GraceAMD Ryzen 3 3100 4-Core Processor - 283,5 tok/s Generation, 3.276 tok/s Prefill, TTFT 3.524 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 3 3100 4-Co...
AMD Ryzen 5 5600X 6-Core Processor 3.484,3 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 290,3 tok/s★ AMD Ryzen 3 3100 4-Core Processor 283,5 tok/s this runNVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) 146,9 tok/sNVIDIA Grace 136,6 tok/s

MBby mainboard

4.5023.3772.2511.1260,02213.3866.5529.718Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 3.484,3 tok/s Generation, 7.781 tok/s Prefill, TTFT 4.659 ms (17 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. PRIME A520M-K - 2.263,7 tok/s Generation, 8.103 tok/s Prefill, TTFT 10.659 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe)ASUSTeK COMPUTER INC....ASUS H7607BA - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe)ASUS H7607BAASUSTeK COMPUTER INC. GX10 - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 283,5 tok/s Generation, 3.276 tok/s Prefill, TTFT 3.524 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 3.484,3 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 2.263,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 290,3 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 283,5 tok/s this runASUS H7607BA 146,9 tok/sASUSTeK COMPUTER INC. GX10 136,6 tok/s

ENGby engine

4.4723.3542.2361.1180,01.3226.09710.87215.647Prefill (tok/s)Generation (tok/s)tensorfold - 3.484,3 tok/s Generation, 7.504 tok/s Prefill, TTFT 6.619 ms (7 Laufe)tensorfoldvLLM - 2.263,7 tok/s Generation, 13.170 tok/s Prefill, TTFT 3.120 ms (13 Laufe)vLLMllama.cpp - 286,2 tok/s Generation, 3.799 tok/s Prefill, TTFT 2.471 ms (37 Laufe) | DIESER LAUF★ llama.cpp
tensorfold 3.484,3 tok/svLLM 2.263,7 tok/s★ llama.cpp 286,2 tok/s this run

DRVby driver

4.5023.3772.2511.1260,01.0953.2735.4517.629Prefill (tok/s)Generation (tok/s)unbekannt - 3.484,3 tok/s Generation, 6.479 tok/s Prefill, TTFT 3.019 ms (54 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)NVIDIA 590.48.01 / CU...
unbekannt 3.484,3 tok/sNVIDIA 590.48.01 / CUDA 13.1 136,6 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 20 W
⚡ TDP 300 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)300 W estimated (TDP)GPU 300 W full load
Avg cost / hourEUR 0.090
Electricity / 1M tokensEUR 0.22
Token / kWh1.35M
Acquisition (system)EUR 1,520 partial priceGPU EUR 1,400 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 3,097
Output tokens (2 years)7.09B
☁️ 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 (20 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

NVIDIA-Nemotron-3.5-Lightning-30B-A3BAMD Radeon AI PRO R9700NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 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.