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

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

Performance benchmark · measured on 29.07.2026 04:52

Benchmark-IDrun-20260729-060802-6982fd
Timebench 3 - Kombi (Prefill + Generation)MoE120BRuntime: llama.cppQuantisierung: Q4_K_M
Generation129,00tok/s
Prefill1.909,17tok/s
Time to First Token1.129,00ms
Total duration18,14s
Concurrency1parallel
Ranking in the field
35of 61 systems

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

This run is better than 43 % of all comparable systems.
Generation 129,0 tok/s
-26 % vs Ø 173,7
Prefill 1.909,2 tok/s
-61 % vs Ø 4.891,8
Time to First Token 1.129 ms
-53 % vs Ø 2.406
Distribution in the field0 – 393 tok/s
Ø 174 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11
393,5 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089
378,6 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-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-643b00
357,0 tok/s
Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032120-4e3476
356,8 tok/s
Qwen3-30B-A3B-Thinking-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032123-b33938
312,1 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032124-ac5167
311,3 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-cecd39
310,2 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-42efc5
309,9 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-abb113
309,5 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-b5f531
304,6 tok/s
Qwen3-Omni-30B-A3B-ThinkingNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032125-29dbef
304,4 tok/s
Qwen3-VL-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032125-021dfb
303,6 tok/s
North-Mini-Code-1.0NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-164528-7e5f02
274,4 tok/s
NVIDIA-Nemotron-3-Super-120B-A12B this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-060802-6982fd
129,0 tok/s

Configuration

benchmark-konfiguration — run-20260729-060802-6982fd
# LLM-Benchmark Konfiguration # Modell : NVIDIA-Nemotron-3-Super-120B-A12B # Engine : llama.cpp # Run-ID : run-20260729-060802-6982fd # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : AMD Ryzen 9 9950X 16-Core Processor # RAM : 92 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--DevQuasar--nvidia.NVIDIA-Nemotron-3-Super-120B-A12B-BF16-GGUF/snapshots/fe70b8fa41864e382a726d44b138588c124d7337/nvidia.NVIDIA-Nemotron-3-Super-120B-A12B-BF16.Q4_K_M-00001-of-00006.gguf \ --alias NVIDIA-Nemotron-3-Super-120B-A12B \ --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
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--DevQuasar--nvidia.NVIDIA-Nemotron-3-Super-120B-A12B-BF16-GGUF/snapshots/fe70b8fa41864e382a726d44b138588c124d7337/nvidia.NVIDIA-Nemotron-3-Super-120B-A12B-BF16.Q4_K_M-00001-of-00006.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 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

7765823881940,009491.8982.847Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 23,3 tok/s Generation, 267 tok/s Prefill, TTFT 58.108 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 600,9 tok/s Generation, 2.334 tok/s Prefill, TTFT 10.016 ms (3 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 600,9 tok/s this runAMD Radeon AI PRO R9700 23,3 tok/s

CPUby processor

7765823881940,009491.8982.847Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 23,3 tok/s Generation, 267 tok/s Prefill, TTFT 58.108 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 600,9 tok/s Generation, 2.334 tok/s Prefill, TTFT 10.016 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 9950X 16-...
★ AMD Ryzen 9 9950X 16-Core Processor 600,9 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 23,3 tok/s

MBby mainboard

7765823881940,009491.8982.847Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 23,3 tok/s Generation, 267 tok/s Prefill, TTFT 58.108 ms (2 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 600,9 tok/s Generation, 2.334 tok/s Prefill, TTFT 10.016 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 600,9 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 23,3 tok/s

ENGby engine

6616316015715411.4171.4771.5381.598Prefill (tok/s)Generation (tok/s)llama.cpp - 600,9 tok/s Generation, 1.507 tok/s Prefill, TTFT 29.253 ms (5 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 600,9 tok/s this run

DRVby driver

6616316015715411.4171.4771.5381.598Prefill (tok/s)Generation (tok/s)unbekannt - 600,9 tok/s Generation, 1.507 tok/s Prefill, TTFT 29.253 ms (5 Laufe)unbekannt
unbekannt 600,9 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 70 W
⚡ TDP 644 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)644 W estimated (TDP)GPU 600 + CPU 29 + Board 15 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 0.42
Token / kWh721.40K
Acquisition (system)EUR 15,248 full priceGPU EUR 13,000 · CPU EUR 649 · Board EUR 499 · RAM EUR 920 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 18,632
Output tokens (2 years)8.14B
☁️ 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 (70 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-A12BNVIDIA 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.