ℹ

For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.

Generation78,10tok/s

Prefill816,43tok/s

Time to First Token627,00ms

Total duration0,00s

Concurrency1parallel

Ranking in the field

This GPU All GPUs

356of 1161 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 69 % of all comparable systems.

Generation 78,1 tok/s

+5 % vs Ø 74,3

Prefill 816,4 tok/s

-65 % vs Ø 2.324,7

Time to First Token 627 ms

-98 % vs Ø 35.657

Distribution in the field0 – 405 tok/s

Ø 74 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004608-16af9b

404,6 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9f766a

395,2 tok/s

Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7

393,5 tok/s

Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11

393,5 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004607-29bd16

388,9 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-1c779f

388,2 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089

378,6 tok/s

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e8b129

377,6 tok/s

Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e

362,3 tok/s

Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085

361,4 tok/s

Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105335-653788

359,4 tok/s

Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090 · run-20260729-105334-2c4905

359,3 tok/s

Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7

359,0 tok/s

Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf

357,1 tok/s

Qwen3-30B-A3B-Instruct-2507 this runIntel Arc Pro B70 · run-20260810-083755-7bd157

78,1 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× concurrent · Generation (tok/s)

NVIDIA GeForce RTX 5090run-20260729-105335-a4aa50

308,5 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032121-b5f531

304,6 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-70b84b

271,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-ef36f2

268,8 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-a68408

268,8 tok/s

NVIDIA GeForce RTX 5090run-20260723-045447-86bc45

232,8 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-004604-055687

204,9 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-060803-3eafe7

195,4 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260724-004603-1cafaf

168,6 tok/s

AMD Radeon PRO W7900 Dual Slotrun-20260817-133237-988951

105,2 tok/s

2× AMD Radeon PRO W7900 Dual Slotrun-20260818-134249-8a0d11

98,8 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165907-cc8f3f

97,6 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165906-f95060

97,6 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165907-b20fe5

91,0 tok/s

Hardware

GPU: Intel Arc Pro B70 · 32 GB VRAM
CPU: AMD Ryzen 9 7945HX with Radeon Graphics
RAM: 61 GB
Mainboard: Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series)

Setup

Runtime: llama.cpp batched-bench SYCL
Quantization: Q4_K_M
Driver: Intel 26.18.38308.4
Model: Qwen3-30B-A3B-Instruct-2507

Anmerkung

llama-batched-bench, 1x Intel Arc Pro B70, npl=1 (pp512/tg128), ngl=99

Configuration

benchmark-konfiguration — run-20260810-083755-7bd157

# LLM-Benchmark Konfiguration # Modell : Qwen3-30B-A3B-Instruct-2507 # Engine : llama.cpp # Run-ID : run-20260810-083755-7bd157 # GPU : Intel Arc Pro B70 # CPU : AMD Ryzen 9 7945HX with Radeon Graphics # RAM : 61 GB bench@llm-benchmark:~$ llama-batched-bench (llama.cpp SYCL) \ --model /root/models/Qwen_Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf \ -ngl 99 \ -c 8192 \ -npl 1

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.	llama-batched-bench (llama.cpp SYCL)
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.	Qwen3-30B-A3B-Instruct-2507
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.	8192
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	/root/models/Qwen_Qwen3-30B-A3B-Instruct-2507-Q4_K_M.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.	99
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	8192
npl	1

All benchmarks of this model To leaderboard

Model comparison

Qwen3-30B-A3B-Instruct-2507 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 1.671,0 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.658,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.515,7 tok/sNVIDIA GeForce RTX 3090 Ti 905,1 tok/sAMD Radeon PRO W7900 Dual Slot 264,2 tok/sNVIDIA GB10 (DGX Spark) 169,9 tok/sNVIDIA GeForce RTX 5070 Ti 152,7 tok/s★ Intel Arc Pro B70 143,6 tok/s this runAMD Radeon 8060S Graphics 107,6 tok/sAMD Radeon AI PRO R9700 97,6 tok/sCPU-only 7,1 tok/s

CPUby processor

AMD Ryzen 7 5800X3D 8-Core Processor 1.671,0 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.658,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.515,7 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 905,1 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 264,2 tok/sNVIDIA Grace 169,9 tok/s★ AMD Ryzen 9 7945HX with Radeon Graphics 143,6 tok/s this runAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 107,6 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 97,6 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 7,1 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.671,0 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.658,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.515,7 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 905,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 264,2 tok/sASUSTeK COMPUTER INC. GX10 169,9 tok/s★ Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 143,6 tok/s this runBosgame AXB35-02 (BeyondMax Series) 107,6 tok/sDell Inc. PowerEdge R820 7,1 tok/s

ENGby engine

★ llama.cpp 1.671,0 tok/s this runvLLM 961,5 tok/sunbekannt 97,6 tok/s

DRVby driver

unbekannt 1.671,0 tok/sNVIDIA 590.48.01 / CUDA 13.1 169,9 tok/s★ Intel 26.18.38308.4 143,6 tok/s this runAMD 7.0.0-27-generic 97,6 tok/s

💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 0 W

⚡ TDP 230 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)230 W estimated (TDP)GPU 230 W full load

Avg cost / hourEUR 0.069

Electricity / 1M tokensEUR 0.25

Token / kWh1.22M

Acquisition (system)EUR 120 missingPSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 1,329

Output tokens (2 years)4.93B

☁️ 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

	Qwen3-30B-A3B-Instruct-2507Intel Arc Pro B70	Qwen3-30B-A3B-Instruct-2507NVIDIA GeForce RTX 5090	Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen3-30B-A3B-Instruct-25073x 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)	–	–	–	–

Intel Arc Pro B70 · this run 78 tok/s NVIDIA GeForce RTX 5090 308 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 305 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 271 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.