ℹ

Public note: Strata 0.1.55, Qwen3.8-Flash-Next GSQ-RCO IQ2_XS auf einer RTX 5090 (32 GB) mit Ryzen 7 5800X3D und 62 GB RAM. Hybrid-Betrieb: Experten im RAM (33 GB), GPU-Expert-Cache 18,7 GB. Serve-Config ueber alle Concurrency-Stufen identisch (8 Batch-Slots, Kontext 32768, KV int8). Node waehrend der Messung exklusiv fuer den Benchmark.

Generation295,95tok/s

Prefill5.286,83tok/s

Time to First Token2.559,00ms

Total duration39,96s

Concurrency5parallel

Ranking in the field

This GPU All GPUs

440of 1521 systems

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

This run is better than 71 % of all comparable systems.

Generation 296,0 tok/s

+15 % vs Ø 258,1

Prefill 5.286,8 tok/s

-3 % vs Ø 5.456,8

Time to First Token 2.559 ms

-91 % vs Ø 29.235

Distribution in the field0 – 1.695 tok/s

Ø 258 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 · run-20261026-180644-b547e8

1.694,7 tok/s

NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 · run-20261026-183943-5ef8b5

1.375,1 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d

1.349,3 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071844-e5e309

1.348,4 tok/s

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-5b4937

1.301,9 tok/s

gemma-4-E2B-it3× 3x 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

NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071851-c3c4a5

1.154,4 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

NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-b22926

1.135,0 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31

1.113,5 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-071836-99dfa5

1.105,8 tok/s

Qwen3.8-Flash-Next this runNVIDIA GeForce RTX 5090 · run-20261101-162845-6354cf

296,0 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20261012-182514-4e244e

804,2 tok/s

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20261012-175110-d711a4

783,6 tok/s

NVIDIA RTX A6000run-20261021-093816-de3d7c

589,5 tok/s

NVIDIA GeForce RTX 3090run-20261013-092430-a14870

572,2 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20261023-180245-a9d038

358,3 tok/s

NVIDIA GeForce RTX 3090run-20261013-165111-67fb02

319,4 tok/s

2× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20261023-180239-f88a7c

302,6 tok/s

NVIDIA GeForce RTX 5090 this runrun-20261101-162845-6354cf

296,0 tok/s

NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20261023-183307-b34ba3

274,1 tok/s

2× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20261023-180238-64ab36

257,2 tok/s

NVIDIA DGX SPARK (GB10)run-20261013-151008-7f1707

246,5 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20261026-133956-cad551

244,9 tok/s

NVIDIA DGX SPARK (GB10)run-20261013-165111-cbe6de

211,2 tok/s

NVIDIA RTX A6000run-20261021-093816-46f946

139,6 tok/s

Hardware

GPU: NVIDIA GeForce RTX 5090 · 32 GB VRAM
CPU: AMD Ryzen 7 5800X3D 8-Core Processor
RAM: 63 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: strata
Quantization: IQ2_XS
Model: Qwen3.8-Flash-Next

Configuration

benchmark-konfiguration — run-20261101-162845-6354cf

# LLM-Benchmark Konfiguration # Modell : Qwen3.8-Flash-Next # Engine : strata # Run-ID : run-20261101-162845-6354cf # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 63 GB bench@llm-benchmark:~$ strata \ --model Qwen3.8-Flash-Next-GSQ-RCO-IQ2_XS

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.	strata
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	32768
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Qwen3.8-Flash-Next 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 Max-Q Workstation Edition 1.564,6 tok/sNVIDIA RTX A6000 1.171,8 tok/sNVIDIA GeForce RTX 3090 1.132,7 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 584,1 tok/sNVIDIA DGX SPARK (GB10) 492,8 tok/s★ NVIDIA GeForce RTX 5090 346,0 tok/s this runNVIDIA Tesla V100 PCIe 32GB 196,2 tok/sAMD Radeon RX 7900 XTX 18,7 tok/s

CPUby processor

AMD Ryzen 9 7945HX with Radeon Graphics 1.564,6 tok/sAMD Ryzen Threadripper PRO 3945WX 12-Cores 1.171,8 tok/sAMD Ryzen 5 5600X 6-Core Processor 1.132,7 tok/sAMD Ryzen 9 9950X 16-Core Processor 584,1 tok/sNVIDIA Grace 492,8 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 424,2 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 346,0 tok/s this runAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 196,2 tok/sAMD EPYC 7203P 8-Core Processor 79,2 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 63,2 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 18,7 tok/s

MBby mainboard

Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 1.564,6 tok/sunbekannt 1.171,8 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.132,7 tok/s this runASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 584,1 tok/sASUSTeK COMPUTER INC. GX10 492,8 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 424,2 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 196,2 tok/sASRockRack ROMED8-2T/BCM 79,2 tok/sDell Inc. PowerEdge R820 63,2 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 35,4 tok/s

ENGby engine

★ strata 1.564,6 tok/s this runllama.cpp 1.555,3 tok/sunbekannt 1.171,8 tok/svLLM 584,1 tok/stensorfold 344,4 tok/s

DRVby driver

unbekannt 1.564,6 tok/sNVIDIA 590.48.01 / CUDA 13.1 492,8 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 72 W

⚡ TDP 622 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load

Avg cost / hourEUR 0.19

Electricity / 1M tokensEUR 0.18

Token / kWh1.71M

Acquisition (system)EUR 4,482 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 504 · PSU EUR 180

Electricity (2 years)–

TCO (2 years)EUR 7,749

Output tokens (2 years)18.67B

☁️ 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 (72 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

	Qwen3.8-Flash-NextNVIDIA GeForce RTX 5090	Qwen3.8-Flash-NextNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Qwen3.8-Flash-NextNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Qwen3.8-Flash-NextNVIDIA RTX A6000
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 5090 · this run 296 tok/s NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 804 tok/s NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 784 tok/s NVIDIA RTX A6000 589 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.