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

NVIDIA-Nemotron-3-Super-120B-A12B-Q8

Performance benchmark · measured on 01.08.2026 12:12

Benchmark-IDrun-20260803-043844-2f15a7
Timebench 3 - Kombi (Prefill + Generation)MoE120BRuntime: llama.cppQuantisierung: Q8_0
Generation422,61tok/s
Prefill2.700,54tok/s
Time to First Token27.527,00ms
Total duration157,60s
Concurrency10parallel
Ranking in the field
135of 204 systems

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

This run is better than 34 % of all comparable systems.
Generation 422,6 tok/s
-50 % vs Ø 849,0
Prefill 2.700,5 tok/s
-61 % vs Ø 6.900,9
Time to First Token 27.527 ms
-11 % vs Ø 30.862
Distribution in the field3 – 2.144 tok/s
Ø 849 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 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-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
Ornith-1.0-35B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260731-071556-e9a354
1.799,4 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032120-1cc62d
1.742,1 tok/s
Nemotron-Cascade-2-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-3fa079
1.655,2 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105341-be087a
1.654,6 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-2fab14
1.651,0 tok/s
Nemotron-Cascade-2-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-b8a790
1.650,7 tok/s
NVIDIA-Nemotron-3-Super-120B-A12B-Q8 this run3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260803-043844-2f15a7
422,6 tok/s

How does this benchmark compare on other GPUs?

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

Configuration

benchmark-konfiguration — run-20260803-043844-2f15a7
# LLM-Benchmark Konfiguration # Modell : NVIDIA-Nemotron-3-Super-120B-A12B-Q8 # Engine : llama.cpp # Run-ID : run-20260803-043844-2f15a7 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--unsloth--NVIDIA-Nemotron-3-Super-120B-A12B-GGUF/snapshots/036038fb30334a2d56a146c6f0d4871ab5edccbb/Q8_0/NVIDIA-Nemotron-3-Super-120B-A12B-Q8_0-00001-of-00004.gguf \ --alias NVIDIA-Nemotron-3-Super-120B-A12B-Q8 \ --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.NVIDIA-Nemotron-3-Super-120B-A12B-Q8
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./home/godcore/.cache/huggingface/hub/models--unsloth--NVIDIA-Nemotron-3-Super-120B-A12B-GGUF/snapshots/036038fb30334a2d56a146c6f0d4871ab5edccbb/Q8_0/NVIDIA-Nemotron-3-Super-120B-A12B-Q8_0-00001-of-00004.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

NVIDIA-Nemotron-3-Super-120B-A12B-Q8 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

5484112741370,006831.3662.050Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 12,2 tok/s Generation, 87 tok/s Prefill, TTFT 106.090 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 423,3 tok/s Generation, 1.666 tok/s Prefill, TTFT 40.463 ms (9 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 423,3 tok/s this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition 12,2 tok/s

CPUby processor

5484112741370,006831.3662.050Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 12,2 tok/s Generation, 87 tok/s Prefill, TTFT 106.090 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 423,3 tok/s Generation, 1.666 tok/s Prefill, TTFT 40.463 ms (9 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 423,3 tok/s this runAMD Ryzen 9 9950X 16-Core Processor 12,2 tok/s

MBby mainboard

5484112741370,006831.3662.050Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 12,2 tok/s Generation, 87 tok/s Prefill, TTFT 106.090 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 423,3 tok/s Generation, 1.666 tok/s Prefill, TTFT 40.463 ms (9 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 423,3 tok/s this runASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 12,2 tok/s

ENGby engine

4664444234023811.1951.2461.2961.347Prefill (tok/s)Generation (tok/s)llama.cpp - 423,3 tok/s Generation, 1.271 tok/s Prefill, TTFT 56.870 ms (12 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 423,3 tok/s this run

DRVby driver

4664444234023811.1951.2461.2961.347Prefill (tok/s)Generation (tok/s)unbekannt - 423,3 tok/s Generation, 1.271 tok/s Prefill, TTFT 56.870 ms (12 Laufe)unbekannt
unbekannt 423,3 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.19
Token / kWh1.55M
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)26.65B
☁️ 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 (165 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-Super-120B-A12B-Q83x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionNVIDIA-Nemotron-3-Super-120B-A12B-Q83x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionNVIDIA-Nemotron-3-Super-120B-A12B-Q83x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionNVIDIA-Nemotron-3-Super-120B-A12B-Q8NVIDIA RTX PRO 6000 Blackwell Workstation Edition
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.