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

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

Performance benchmark · measured on 30.07.2026 21:27

Benchmark-IDrun-20260731-071555-0da588
Timebench 3 - Kombi (Prefill + Generation)MoE120BRuntime: llama.cppQuantisierung: Q4_K_M
Generation16,07tok/s
Prefill104,10tok/s
Time to First Token170.078,00ms
Total duration1.200,00s
Concurrency5parallel
Ranking in the field
481of 545 systems

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

This run is better than 12 % of all comparable systems.
Generation 16,1 tok/s
-96 % vs Ø 382,4
Prefill 104,1 tok/s
-98 % vs Ø 5.252,6
Time to First Token 170.078 ms
+440 % vs Ø 31.476
Distribution in the field0 – 1.349 tok/s
Ø 379 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d
1.349,3 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-5b4937
1.301,9 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-4111a9
1.195,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-5432cd
1.164,8 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9
1.136,3 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-09627f
1.135,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31
1.113,5 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91
1.090,6 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818
1.071,0 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92
1.051,1 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a
1.015,5 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
NVIDIA-Nemotron-3-Super-120B-A12B this runNVIDIA GeForce RTX 3090 Ti · run-20260731-071555-0da588
16,1 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× concurrent · Generation (tok/s)

Configuration

benchmark-konfiguration — run-20260731-071555-0da588
# LLM-Benchmark Konfiguration # Modell : NVIDIA-Nemotron-3-Super-120B-A12B # Engine : llama.cpp # Run-ID : run-20260731-071555-0da588 # GPU : NVIDIA GeForce RTX 3090 Ti # CPU : AMD Ryzen 9 8945HX with Radeon Graphics # RAM : 92 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.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 12 \ -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./root/.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.12
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

7775833891940,009581.9172.875Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 600,9 tok/s Generation, 2.334 tok/s Prefill, TTFT 10.016 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5070 Ti - 32,6 tok/s Generation, 110 tok/s Prefill, TTFT 130.902 ms (3 Laufe)NVIDIA GeForce RTX 50...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 GeForce RTX 3090 Ti - 18,9 tok/s Generation, 106 tok/s Prefill, TTFT 171.396 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 30...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 600,9 tok/sNVIDIA GeForce RTX 5070 Ti 32,6 tok/sAMD Radeon AI PRO R9700 23,3 tok/s★ NVIDIA GeForce RTX 3090 Ti 18,9 tok/s this run

CPUby processor

7775833891940,009581.9172.875Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 600,9 tok/s Generation, 2.334 tok/s Prefill, TTFT 10.016 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 32,6 tok/s Generation, 110 tok/s Prefill, TTFT 130.902 ms (3 Laufe)AMD Ryzen Threadrippe...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 8945HX with Radeon Graphics - 18,9 tok/s Generation, 106 tok/s Prefill, TTFT 171.396 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 8945HX wi...
AMD Ryzen 9 9950X 16-Core Processor 600,9 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 32,6 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 23,3 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 18,9 tok/s this run

MBby mainboard

7775833891940,009581.9172.875Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 600,9 tok/s Generation, 2.334 tok/s Prefill, TTFT 10.016 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 32,6 tok/s Generation, 110 tok/s Prefill, TTFT 130.902 ms (3 Laufe)ASUSTeK COMPUTER INC....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....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 18,9 tok/s Generation, 106 tok/s Prefill, TTFT 171.396 ms (3 Laufe) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 600,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 32,6 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 23,3 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 18,9 tok/s this run

ENGby engine

661631601571541699729759789Prefill (tok/s)Generation (tok/s)llama.cpp - 600,9 tok/s Generation, 744 tok/s Prefill, TTFT 95.742 ms (11 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 600,9 tok/s this run

DRVby driver

661631601571541699729759789Prefill (tok/s)Generation (tok/s)unbekannt - 600,9 tok/s Generation, 744 tok/s Prefill, TTFT 95.742 ms (11 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 (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 50 W
⚡ TDP 477 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)477 W estimated (TDP)GPU 450 + CPU 17 + Board 10 W full load
Avg cost / hourEUR 0.14
Electricity / 1M tokensEUR 2.47
Token / kWh121.22K
Acquisition (system)EUR 2,986 partial priceGPU EUR 999 · CPU EUR 549 · RAM EUR 1,288 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 5,494
Output tokens (2 years)1.01B
☁️ 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 (50 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 GeForce RTX 3090 TiNVIDIA-Nemotron-3-Super-120B-A12BNVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA-Nemotron-3-Super-120B-A12BNVIDIA GeForce RTX 5070 TiNVIDIA-Nemotron-3-Super-120B-A12B3x AMD 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.