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 466,1 tok/sNVIDIA GeForce RTX 5090 438,4 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 397,5 tok/s★ NVIDIA GeForce RTX 3090 Ti 174,1 tok/s this runNVIDIA GeForce RTX 5070 Ti 42,0 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 466,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 438,4 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 397,5 tok/s★ AMD Ryzen 5 5600X 6-Core Processor 174,1 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 42,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,5 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 466,1 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 438,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 397,5 tok/s★ ASUSTeK COMPUTER INC. PRIME A520M-K 174,1 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 42,0 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 19,5 tok/s

ENGby engine

llama.cpp 466,1 tok/sunbekannt 174,1 tok/s

DRVby driver

unbekannt 466,1 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 URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 25 W

⚡ TDP 450 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)450 W estimated (TDP)GPU 450 W full load

Avg cost / hourEUR 0.14

Electricity / 1M tokensEUR 0.46

Token / kWh650.80K

Acquisition (system)EUR 1,149 partial priceGPU EUR 999 · PSU EUR 150

Electricity (2 years)–

TCO (2 years)EUR 3,514

Output tokens (2 years)5.13B

☁️ 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 (25 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-4-31B-itNVIDIA GeForce RTX 3090 Ti	gemma-4-31B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gemma-4-31B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gemma-4-31B-itNVIDIA GeForce RTX 5090
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 GeForce RTX 3090 Ti · this run 81 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 248 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 247 tok/s NVIDIA GeForce RTX 5090 239 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

Marcel Sommer

@marcelsommer