ℹ

Public note: Rechnerische Variante: Messwerte der NVIDIA RTX PRO 6000 Blackwell Workstation Edition (gemessen auf godcore-ai-002) uebertragen auf die Host-Konfiguration von godcore-worker-004 (AMD Ryzen 5 5600X, 32 GB RAM). Keine eigene Messung dieser Kombination. Quelle: run-20260728-194137-302ce3 (2026-07-28 19:37:22).

Generation1.103,42tok/s

Prefill5.051,32tok/s

Time to First Token11.207,00ms

Total duration65,40s

Concurrency10parallel

Ranking in the field

This GPU All GPUs

175of 1459 systems

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

This run is better than 88 % of all comparable systems.

Generation 1.103,4 tok/s

+147 % vs Ø 447,4

Prefill 5.051,3 tok/s

-26 % vs Ø 6.827,2

Time to First Token 11.207 ms

-75 % vs Ø 44.979

Distribution in the field0 – 2.491 tok/s

Ø 447 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-A3BNVIDIA 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

gemma-4-12B-it this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071859-ddb9c0

1.103,4 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260728-194137-302ce3

1.104,3 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Edition this runrun-20261023-071859-ddb9c0

1.103,4 tok/s

NVIDIA GeForce RTX 5090run-20260729-060805-568759

1.058,9 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105332-19f510

1.041,8 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105332-1d34ac

1.007,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105332-d2c914

947,5 tok/s

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260923-143546-4d50d9

861,4 tok/s

2× NVIDIA RTX A6000run-20260829-110114-b3f1dc

681,8 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260728-194136-c688b4

677,5 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-032127-ace117

654,9 tok/s

2× NVIDIA RTX A6000run-20260827-073158-8268ef

611,0 tok/s

2× NVIDIA RTX A6000run-20260829-113415-7f3c22

561,5 tok/s

2× NVIDIA RTX A6000run-20260827-083601-0d291a

513,5 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-032759-8c9d3d

486,2 tok/s

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen 5 5600X 6-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: llama.cpp
Quantization: UD-Q4_K_XL
Model: gemma-4-12B-it

Configuration

benchmark-konfiguration — run-20261023-071859-ddb9c0

# LLM-Benchmark Konfiguration # Modell : gemma-4-12B-it # Engine : llama.cpp # Run-ID : run-20261023-071859-ddb9c0 # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : AMD Ryzen 5 5600X 6-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/.cache/huggingface/hub/models--unsloth--gemma-4-12B-it-qat-GGUF/snapshots/980b060c40a8539ac159e0501a3e0f66a6365af3/gemma-4-12B-it-qat-UD-Q4_K_XL.gguf \ -c 16384 \ -np 12

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.	gemma-4-12B-it
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--gemma-4-12B-it-qat-GGUF/snapshots/980b060c40a8539ac159e0501a3e0f66a6365af3/gemma-4-12B-it-qat-UD-Q4_K_XL.gguf
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	16384
np	12
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

gemma-4-12B-it 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

★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.104,3 tok/s this runNVIDIA GeForce RTX 5090 1.058,9 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.041,8 tok/sNVIDIA RTX A6000 681,8 tok/sNVIDIA GeForce RTX 5070 Ti 677,5 tok/sNVIDIA GeForce RTX 3090 Ti 654,9 tok/sAMD Radeon RX 7900 XTX 212,9 tok/sAMD Radeon PRO W7800 48GB 202,0 tok/sAMD Radeon AI PRO R9700 188,8 tok/sNVIDIA Tesla V100 PCIe 32GB 186,2 tok/sNVIDIA GeForce RTX 2060 89,8 tok/sNVIDIA Tesla P100 PCIe 16GB 45,8 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.104,3 tok/s★ AMD Ryzen 5 5600X 6-Core Processor 1.103,4 tok/s this runAMD Ryzen 7 5800X3D 8-Core Processor 1.058,9 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.041,8 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 861,4 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 681,8 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 677,5 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 654,9 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 212,9 tok/sAMD Ryzen 3 3100 4-Core Processor 188,8 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 186,2 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 179,4 tok/sIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz 89,8 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.104,3 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.103,4 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.041,8 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 861,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 677,5 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 654,9 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 372,4 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 188,8 tok/sDell Inc. PowerEdge R820 179,4 tok/sASRock H110 Pro BTC+ 89,8 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 45,8 tok/s

ENGby engine

★ llama.cpp 1.104,3 tok/s this runvLLM 861,4 tok/s

DRVby driver

unbekannt 1.104,3 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 URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 42 W

⚡ TDP 612 W

☁️ External LLM (API) show

Input €/1M Output €/1M Input per output token

Electricity0.30 EUR/kWh

Avg power (incl. idle)612 W estimated (TDP)GPU 600 + Board 12 W full load

Avg cost / hourEUR 0.18

Electricity / 1M tokensEUR 0.046

Token / kWh6.49M

Acquisition (system)EUR 13,698 full priceGPU EUR 13,000 · CPU EUR 121 · Board EUR 149 · RAM EUR 248 · PSU EUR 180

Electricity (2 years)–

TCO (2 years)EUR 16,915

Output tokens (2 years)69.59B

☁️ 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 (42 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

	gemma-4-12B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gemma-4-12B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gemma-4-12B-itNVIDIA GeForce RTX 5090	gemma-4-12B-it3x NVIDIA RTX PRO 6000 Blackwell Max-Q 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)	–	–	–	–

NVIDIA RTX PRO 6000 Blackwell Workstation Edition · this run 1,103 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,104 tok/s NVIDIA GeForce RTX 5090 1,059 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,042 tok/s

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.