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

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

Performance benchmark · measured on 24.10.2026 13:32

Benchmark-IDrun-20261024-130444-421699
Timebench 3 - Kombi (Prefill + Generation)MoE31.6BRuntime: llama.cppQuantisierung: Q4_0
Generation72,08tok/s
Prefill1.292,53tok/s
Time to First Token1.669,30ms
Total duration52,56s
Concurrency1parallel
Ranking in the field
721of 1836 systems

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

This run is better than 61 % of all comparable systems.
Generation 72,1 tok/s
-7 % vs Ø 77,3
Prefill 1.292,5 tok/s
-54 % vs Ø 2.839,0
Time to First Token 1.669 ms
-93 % vs Ø 24.818
Distribution in the field0 – 405 tok/s
Ø 77 Median Dieser Lauf

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
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
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf
357,1 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3B this runNVIDIA RTX SPARK (N1X) · run-20261024-130444-421699
72,1 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA RTX SPARK (N1X)
CPU: NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)
RAM: 128 GB
Mainboard: ASUS H7607BA

Setup

Runtime: llama.cpp
Quantization: Q4_0
Model: NVIDIA-Nemotron-3.5-Lightning-30B-A3B

Configuration

benchmark-konfiguration — run-20261024-130444-421699
# LLM-Benchmark Konfiguration # Modell : NVIDIA-Nemotron-3.5-Lightning-30B-A3B # Engine : llama.cpp # Run-ID : run-20261024-130444-421699 # GPU : NVIDIA RTX SPARK (N1X) # CPU : NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) # RAM : 128 GB bench@llm-benchmark:~$ 'C:\Users\mail\.lmstudio\extensions\backends\llama.cpp-win-arm64-nvidia-cuda13-2.61.0\llama-server.exe' \ --model 'C:\Users\mail\Documents\Codex\2026-10-24\mach\work\models\NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf' \ --alias benchmark-local \ --host 127.0.0.1 \ --port 18764 \ --device CUDA0 \ --gpu-layers all \ --ctx-size 8192 \ --parallel 1 \ --threads 20 \ --threads-batch 20 \ --batch-size 1024 \ --ubatch-size 256 \ --flash-attn on \ --fit on \ --fit-unified-limit 107656 \ --fit-device-limit 61522 \ --no-cache-prompt \ --no-cache-idle-slots \ --cache-ram 0 \ --spec-type none \ --metrics
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-3.5-Lightning-30B-A3B
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.8192
Batch-Groesse?Logische Batchgroesse fuer die Prompt-Verarbeitung (Anzahl Token pro Prefill-Durchlauf).1024
cache-ram0
deviceCUDA0
fiton
fit-device-limit61522
fit-unified-limit107656
Flash Attention?FlashAttention fuer schnellere und speichersparende Attention. Wert on/off/auto je nach Build.on
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.all
metricsaktiv
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.C:\Users\mail\Documents\Codex\2026-10-24\mach\work\models\NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_0.gguf
no-cache-idle-slotsaktiv
no-cache-promptaktiv
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.1
spec-typenone
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).20
Batch-Threads?Anzahl CPU-Threads fuer Prompt-Verarbeitung und Batch (Prefill).20
Micro-Batch?Physische Micro-Batchgroesse. Begrenzt, wie viele Token gleichzeitig durch die Compute-Pipeline laufen.256
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
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

2.9162.1871.4587290,003.2706.5409.810Prefill (tok/s)Generation (tok/s)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...AMD Radeon AI PRO R9700 - 290,3 tok/s Generation, 6.285 tok/s Prefill, TTFT 963 ms (30 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 3090 - 140,0 tok/s Generation, 1.321 tok/s Prefill, TTFT 8.770 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA DGX SPARK (GB10) - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)NVIDIA DGX SPARK (GB1...NVIDIA RTX SPARK (N1X) - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe) | DIESER LAUF★ NVIDIA RTX SPARK (N1X)
NVIDIA GeForce RTX 3090 Ti 2.263,7 tok/sAMD Radeon AI PRO R9700 290,3 tok/s★ NVIDIA RTX SPARK (N1X) 146,9 tok/s this runNVIDIA GeForce RTX 3090 140,0 tok/sNVIDIA DGX SPARK (GB10) 136,6 tok/s

CPUby processor

2.9162.1871.4587290,05773.0105.4447.877Prefill (tok/s)Generation (tok/s)AMD Ryzen 5 5600X 6-Core Processor - 2.263,7 tok/s Generation, 4.712 tok/s Prefill, TTFT 9.714 ms (6 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...AMD Ryzen 3 3100 4-Core Processor - 283,5 tok/s Generation, 3.276 tok/s Prefill, TTFT 3.524 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...NVIDIA Grace - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)NVIDIA GraceNVIDIA 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) | DIESER LAUF★ NVIDIA RTX Spark N1X ...
AMD Ryzen 5 5600X 6-Core Processor 2.263,7 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 290,3 tok/sAMD Ryzen 3 3100 4-Core Processor 283,5 tok/s★ NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) 146,9 tok/s this runNVIDIA Grace 136,6 tok/s

MBby mainboard

2.9162.1871.4587290,003.2706.5409.810Prefill (tok/s)Generation (tok/s)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....ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 283,5 tok/s Generation, 3.276 tok/s Prefill, TTFT 3.524 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 140,0 tok/s Generation, 1.321 tok/s Prefill, TTFT 8.770 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. GX10 - 136,6 tok/s Generation, 2.246 tok/s Prefill, TTFT 5.100 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUS H7607BA - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe) | DIESER LAUF★ ASUS H7607BA
ASUSTeK COMPUTER INC. PRIME A520M-K 2.263,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 290,3 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 283,5 tok/s★ ASUS H7607BA 146,9 tok/s this runASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 140,0 tok/sASUSTeK COMPUTER INC. GX10 136,6 tok/s

ENGby engine

2.8862.1641.4437210,08706.57412.27817.982Prefill (tok/s)Generation (tok/s)vLLM - 2.263,7 tok/s Generation, 15.053 tok/s Prefill, TTFT 5.666 ms (6 Laufe)vLLMllama.cpp - 286,2 tok/s Generation, 3.799 tok/s Prefill, TTFT 2.471 ms (37 Laufe) | DIESER LAUF★ llama.cpp
vLLM 2.263,7 tok/s★ llama.cpp 286,2 tok/s this run

DRVby driver

2.9162.1871.4587290,01.3053.0524.7986.544Prefill (tok/s)Generation (tok/s)unbekannt - 2.263,7 tok/s Generation, 5.604 tok/s Prefill, TTFT 2.753 ms (40 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 2.263,7 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 %
🔌 Idle 0 W
⚡ TDP 10 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)0 W missing
Avg cost / hour–
Electricity / 1M tokens–
Token / kWh–
Acquisition (system)– missing
Electricity (2 years)–
TCO (2 years)–
Output tokens (2 years)4.55B
☁️ External LLM (API) – comparison
External LLM cost (2 years)–
Savings vs. external (2 years)–
No power draw measured – values estimated from GPU TDP + CPU (idle + 15 %) + board.

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 (0 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-A3BNVIDIA RTX SPARK (N1X)NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 TiNVIDIA-Nemotron-3.5-Lightning-30B-A3BAMD Radeon AI PRO R9700NVIDIA-Nemotron-3.5-Lightning-30B-A3BAMD Radeon AI PRO R9700
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.