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

Nemotron-3.5-Lightning-30B-A3B

Performance benchmark · measured on 17.08.2026 20:48

Benchmark-IDrun-20260817-212317-eaf7ea
Timebench 3 - Kombi (Prefill + Generation)Hybrid Mamba-2 + MoE (3B aktiv)30BRuntime: vLLMQuantisierung: BF16
Generation170,48tok/s
Prefill23.477,42tok/s
Time to First Token582,00ms
Total duration61,32s
Concurrency5parallel
Ranking in the field
35of 203 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 83 % of all comparable systems.
Generation 170,5 tok/s
+114 % vs Ø 79,5
Prefill 23.477,4 tok/s
+1.248 % vs Ø 1.742,0
Time to First Token 582 ms
-99 % vs Ø 81.026
Distribution in the field0 – 382 tok/s
Ø 80 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

Hardware

GPU: 4x AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: vLLM
Quantization: BF16
Model: Nemotron-3.5-Lightning-30B-A3B

Configuration

benchmark-konfiguration — run-20260817-212317-eaf7ea
# LLM-Benchmark Konfiguration # Modell : Nemotron-3.5-Lightning-30B-A3B # Engine : vLLM # Run-ID : run-20260817-212317-eaf7ea # GPU : 4x AMD Radeon AI PRO R9700 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ vllm serve \ --model NVIDIA-Nemotron-3.5-Lightning-30B-A3B
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.vllm
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

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

3193052902762616.2226.4876.7517.016Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
★ AMD Radeon AI PRO R9700 290,3 tok/s this run

CPUby processor

3193052902762616.2226.4876.7517.016Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 290,3 tok/s this run

MBby mainboard

3193052902762616.2226.4876.7517.016Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 290,3 tok/s this run

ENGby engine

3203042882722562608.98617.71226.438Prefill (tok/s)Generation (tok/s)llama.cpp - 286,2 tok/s Generation, 4.696 tok/s Prefill, TTFT 679 ms (24 Laufe)llama.cppvLLM - 290,3 tok/s Generation, 22.003 tok/s Prefill, TTFT 674 ms (3 Laufe) | DIESER LAUF★ vLLM
★ vLLM 290,3 tok/s this runllama.cpp 286,2 tok/s

DRVby driver

3193052902762616.2226.4876.7517.016Prefill (tok/s)Generation (tok/s)unbekannt - 290,3 tok/s Generation, 6.619 tok/s Prefill, TTFT 679 ms (27 Laufe)unbekannt
unbekannt 290,3 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (5× 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 85 W
⚡ TDP 371 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)371 W estimated (TDP)GPU 300 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 0.18
Token / kWh1.65M
Acquisition (system)EUR 6,824 full priceGPU EUR 1,400 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 8,774
Output tokens (2 years)10.75B
☁️ 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 (85 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-A3BAMD Radeon AI PRO R9700Nemotron-3.5-Lightning-30B-A3BAMD Radeon AI PRO R9700Nemotron-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.