# LLM-Benchmark Konfiguration # Modell : Qwen3.6-35B-A3B # Engine : vLLM # Run-ID : run-20260817-204953-91cbae # GPU : AMD Radeon PRO W7900 Dual Slot # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 GB bench@llm-benchmark:~$ vllm serve /root/.cache/huggingface/hub/models--cyankiwi--Qwen3.6-35B-A3B-AWQ-4bit/snapshots/00fcea2d3bcf5389b518d4fc082e5590e0ba4844 \ --served-model-name Qwen3.6-35B-A3B \ --max-model-len 8192 \ --gpu-memory-utilization 0.90 \ --trust-remote-code \ --host 0.0.0.0 \ --port 8000

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
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.	Qwen3.6-35B-A3B
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.	Qwen3.6-35B-A3B
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	8192
GPU-Speicher?Anteil des GPU-Speichers (0 bis 1), den vLLM belegen darf. 0.92 = 92 %. Hoeher = mehr Platz fuer den KV-Cache (mehr/laengere parallele Anfragen), aber groesseres Risiko fuer 'Out of Memory'.	0.90

All benchmarks of this model To leaderboard

Model comparison

Qwen3.6-35B-A3B 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 1.489,1 tok/sNVIDIA GeForce RTX 5090 1.409,4 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.367,3 tok/sNVIDIA GeForce RTX 3090 Ti 852,0 tok/s★ AMD Radeon PRO W7900 Dual Slot 296,2 tok/s this runAMD Radeon AI PRO R9700 271,4 tok/sNVIDIA GB10 (DGX Spark) 167,1 tok/sNVIDIA GeForce RTX 5070 Ti 142,9 tok/sIntel Arc Pro B70 124,5 tok/sAMD Radeon 8060S Graphics 98,3 tok/sCPU-only 4,3 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.489,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.409,4 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.367,3 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 852,0 tok/sAMD Ryzen 5 5600X 6-Core Processor 830,5 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 296,2 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 271,4 tok/sNVIDIA Grace 167,1 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 124,5 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 98,3 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 4,3 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.489,1 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.409,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.367,3 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 852,0 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 830,5 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 296,2 tok/s this runASUSTeK COMPUTER INC. GX10 167,1 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 124,5 tok/sBosgame AXB35-02 (BeyondMax Series) 98,3 tok/sDell Inc. PowerEdge R820 4,3 tok/s

ENGby engine

llama.cpp 1.489,1 tok/s★ vLLM 952,8 tok/s this rununbekannt 830,5 tok/s

DRVby driver

unbekannt 1.489,1 tok/sNVIDIA 590.48.01 / CUDA 13.1 167,1 tok/sIntel 26.18.38308.4 124,5 tok/sAMD 7.0.0-27-generic 79,4 tok/s

💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 10 W

⚡ TDP 305 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)305 W estimated (TDP)GPU 295 + Board 10 W full load

Avg cost / hourEUR 0.092

Electricity / 1M tokensEUR 0.17

Token / kWh1.77M

Acquisition (system)EUR 2,126 missingRAM EUR 1,976 · PSU EUR 150

Electricity (2 years)–

TCO (2 years)EUR 3,729

Output tokens (2 years)9.44B

☁️ 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

	Qwen3.6-35B-A3BAMD Radeon PRO W7900 Dual Slot	Qwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen3.6-35B-A3BNVIDIA GeForce RTX 5090	Qwen3.6-35B-A3B3x 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 W7900 Dual Slot · this run 150 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1,489 tok/s NVIDIA GeForce RTX 5090 1,409 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1,367 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.