# LLM-Benchmark Konfiguration # Modell : Meta-Llama-3.1-8B-Instruct # Engine : vLLM # Run-ID : run-20261020-050732-5c0812 # GPU : AMD Radeon PRO W7800 48GB # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 62 GB bench@llm-benchmark:~$ vllm serve

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.	vllm
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Meta-Llama-3.1-8B-Instruct 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 GeForce RTX 5090 1.593,1 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.533,0 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.433,0 tok/sNVIDIA RTX A6000 1.026,4 tok/sNVIDIA GeForce RTX 5070 Ti 913,4 tok/sNVIDIA GeForce RTX 3090 Ti 837,9 tok/sAMD Radeon AI PRO R9700 518,3 tok/sNVIDIA GeForce RTX 4090 489,7 tok/sAMD Radeon RX 7900 XTX 405,0 tok/s★ AMD Radeon PRO W7800 48GB 323,1 tok/s this runNVIDIA GeForce RTX 2060 169,0 tok/sNVIDIA Tesla V100 PCIe 32GB 122,6 tok/sNVIDIA Tesla P100 PCIe 16GB 67,6 tok/sIntel Arc Pro B70 66,4 tok/sCPU-only 3,6 tok/s

CPUby processor

AMD Ryzen 7 5800X3D 8-Core Processor 1.593,1 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.533,0 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.433,0 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 1.026,4 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 913,4 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 837,9 tok/sAMD Ryzen 3 3100 4-Core Processor 489,7 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 405,0 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 266,7 tok/sIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz 130,9 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 122,6 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 67,6 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 3,6 tok/s4 x Cortex-A78C + 4 x Cortex-A55 1,2 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.593,1 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.533,0 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.433,0 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 913,4 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 837,9 tok/sMicro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) 489,7 tok/sDell Inc. PowerEdge R820 266,7 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 258,8 tok/sASRock H110 Pro BTC+ 130,9 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 67,6 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 66,4 tok/sunbekannt 1,2 tok/s

ENGby engine

llama.cpp 1.593,1 tok/s★ vLLM 1.026,4 tok/s this rununbekannt 42,1 tok/s

DRVby driver

unbekannt 1.593,1 tok/sIntel 26.18.38308.4 66,4 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 URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 10 W

⚡ TDP 270 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)270 W estimated (TDP)GPU 260 + Board 10 W full load

Avg cost / hourEUR 0.081

Electricity / 1M tokensEUR 1.15

Token / kWh260.80K

Acquisition (system)EUR 5,304 partial priceGPU EUR 2,808 · CPU EUR 1,880 · RAM EUR 496 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 6,723

Output tokens (2 years)1.23B

☁️ 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 (10 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

	Meta-Llama-3.1-8B-InstructAMD Radeon PRO W7800 48GB	Meta-Llama-3.1-8B-InstructNVIDIA GeForce RTX 5090	Meta-Llama-3.1-8B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Meta-Llama-3.1-8B-Instruct3x 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)	–	–	–	–

AMD Radeon PRO W7800 48GB · this run 20 tok/s NVIDIA GeForce RTX 5090 246 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 239 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 225 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.