# LLM-Benchmark Konfiguration # Modell : Ornith-1.0-9B # Engine : llama.cpp # Run-ID : run-20260907-130632-642038 # GPU : NVIDIA Tesla V100 PCIe 32GB # CPU : AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics # RAM : 61 GB bench@llm-benchmark:~$ llama-server \ -m deepreinforce-ai_Ornith-1.0-9B-Q8_0.gguf \ -ngl 999 \ -fa on \ -c 49152 \ -np 12 '(Tesla' V100-PCIE-32GB 'CUDA)'

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
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	49152
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	deepreinforce-ai_Ornith-1.0-9B-Q8_0.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
fa	on
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	49152
np	12
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Ornith-1.0-9B 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 1.560,5 tok/sNVIDIA GeForce RTX 5090 1.505,6 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.349,7 tok/sNVIDIA RTX A6000 1.062,5 tok/sNVIDIA GeForce RTX 5070 Ti 883,4 tok/sNVIDIA GeForce RTX 3090 Ti 786,2 tok/sAMD Radeon AI PRO R9700 487,6 tok/sIntel Arc Pro B70 351,6 tok/sAMD Radeon PRO W7800 48GB 294,0 tok/s★ NVIDIA Tesla V100 PCIe 32GB 248,7 tok/s this runAMD Radeon RX 7900 XTX 242,4 tok/sAMD Radeon PRO W7900 Dual Slot 235,1 tok/sNVIDIA GeForce RTX 2060 108,0 tok/sNVIDIA Tesla P100 PCIe 16GB 64,5 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.560,5 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.505,6 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.349,7 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 1.100,7 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 1.062,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 883,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 786,2 tok/s★ AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 248,7 tok/s this runAMD Ryzen Threadripper PRO 3955WX 16-Cores 242,4 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 207,5 tok/sIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz 108,0 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.560,5 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.505,6 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.349,7 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 1.100,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 883,4 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 786,2 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 248,7 tok/s this runDell Inc. PowerEdge R820 207,5 tok/sASRock H110 Pro BTC+ 108,0 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 64,5 tok/s

ENGby engine

★ llama.cpp 1.560,5 tok/s this runvLLM 1.100,7 tok/s

DRVby driver

unbekannt 1.560,5 tok/sIntel 26.18.38308.4 351,6 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 0 W

⚡ TDP 250 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)250 W estimated (TDP)GPU 250 W full load

Avg cost / hourEUR 0.075

Electricity / 1M tokensEUR 0.28

Token / kWh1.07M

Acquisition (system)EUR 720 partial priceGPU EUR 600 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 2,034

Output tokens (2 years)4.69B

☁️ 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 (0 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

	Ornith-1.0-9BNVIDIA Tesla V100 PCIe 32GB	Ornith-1.0-9BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Ornith-1.0-9BNVIDIA GeForce RTX 5090	Ornith-1.0-9B3x 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 Tesla V100 PCIe 32GB · this run 74 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,561 tok/s NVIDIA GeForce RTX 5090 1,506 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,350 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.