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

Nemotron-3.5-Lightning-30B-A3B

Performance benchmark · measured on 24.10.2026 14:15

Benchmark-IDrun-20261024-122729-414d0c
Timebench 3 - Kombi (Prefill + Generation)Hybrid Mamba-2 + MoE (3B aktiv)30BRuntime: llama.cppQuantisierung: Q4_K_M
ℹ
Public note: NVIDIA GB10 (DGX Spark, 120GB Unified Memory) . NVIDIA-Nemotron-3.5-Lightning-30B-A3B Q4_K_M . llama.cpp b10507 native aarch64, -ngl 999, -np 12, -c 49152 (4096 Tok/Slot)
ℹ
For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.
Generation136,58tok/s
Prefill2.934,04tok/s
Time to First Token8.734,00ms
Total duration168,80s
Concurrency10parallel
Ranking in the field
1045of 1479 systems

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

This run is better than 29 % of all comparable systems.
Generation 136,6 tok/s
-69 % vs Ø 445,0
Prefill 2.934,0 tok/s
-57 % vs Ø 6.823,3
Time to First Token 8.734 ms
-80 % vs Ø 44.468
Distribution in the field0 – 2.491 tok/s
Ø 445 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
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065752-48370d
2.412,3 tok/s
Nemotron-3.5-Lightning-30B-A3B same modelNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-dce558
2.263,7 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065758-96fe6a
2.144,3 tok/s
gemma-4-E2B-it3× 3x 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-20260730-035052-9c966e
1.995,4 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065808-332d1f
1.981,1 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
Nemotron-3-Nano-4B3× 3x 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
Nemotron-3.5-Lightning-30B-A3B this runNVIDIA DGX SPARK (GB10) · run-20261024-122729-414d0c
136,6 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA DGX SPARK (GB10) · 128 GB VRAM
CPU: NVIDIA Grace
RAM: 120 GB
Mainboard: ASUSTeK COMPUTER INC. GX10

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Driver: NVIDIA 590.48.01 / CUDA 13.1
Model: Nemotron-3.5-Lightning-30B-A3B

Configuration

benchmark-konfiguration — run-20261024-122729-414d0c
# LLM-Benchmark Konfiguration # Modell : Nemotron-3.5-Lightning-30B-A3B # Engine : llama.cpp # Run-ID : run-20261024-122729-414d0c # GPU : NVIDIA DGX SPARK (GB10) # CPU : NVIDIA Grace # RAM : 120 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/bench_models/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Q4_K_M.gguf \ -ngl 999 \ -np 12 \ -c 49152
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.49152
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
np12
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.49152
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

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 RTX SPARK (N1X) - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe)NVIDIA RTX SPARK (N1X)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) | DIESER LAUF★ NVIDIA DGX SPARK (GB1...
NVIDIA GeForce RTX 3090 Ti 2.263,7 tok/sAMD Radeon AI PRO R9700 290,3 tok/sNVIDIA RTX SPARK (N1X) 146,9 tok/sNVIDIA GeForce RTX 3090 140,0 tok/s★ NVIDIA DGX SPARK (GB10) 136,6 tok/s this run

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 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) | DIESER LAUF★ NVIDIA Grace
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/sNVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) 146,9 tok/s★ NVIDIA Grace 136,6 tok/s this run

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....ASUS H7607BA - 146,9 tok/s Generation, 1.835 tok/s Prefill, TTFT 5.732 ms (4 Laufe)ASUS H7607BAASUSTeK 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) | DIESER LAUF★ ASUSTeK COMPUTER INC....
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/sASUS H7607BA 146,9 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 140,0 tok/s★ ASUSTeK COMPUTER INC. GX10 136,6 tok/s this run

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) | DIESER LAUF★ NVIDIA 590.48.01 / CU...
unbekannt 2.263,7 tok/s★ NVIDIA 590.48.01 / CUDA 13.1 136,6 tok/s this run
💰 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 15 W
⚡ TDP 140 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)140 W estimated (TDP)GPU 140 W full load
Avg cost / hourEUR 0.042
Electricity / 1M tokensEUR 0.085
Token / kWh3.51M
Acquisition (system)EUR 5,800 partial priceGPU EUR 4,000 · RAM EUR 1,680 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 6,536
Output tokens (2 years)8.61B
☁️ 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 (15 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-3.5-Lightning-30B-A3BNVIDIA DGX SPARK (GB10)Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 TiNemotron-3.5-Lightning-30B-A3BAMD Radeon AI PRO R9700Nemotron-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.