ℹ

Public note: llama-batched-bench, 1x Intel Arc Pro B70, npl=5 (pp512/tg128), ngl=99

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.

Generation140,06tok/s

Prefill1.283,76tok/s

Time to First Token1.994,00ms

Total duration0,00s

Concurrency5parallel

Ranking in the field

This GPU All GPUs

806of 1469 systems

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

This run is better than 45 % of all comparable systems.

Generation 140,1 tok/s

-43 % vs Ø 246,5

Prefill 1.283,8 tok/s

-76 % vs Ø 5.365,8

Time to First Token 1.994 ms

-93 % vs Ø 30.155

Distribution in the field0 – 1.349 tok/s

Ø 247 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

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

1.349,3 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

Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864

1.188,7 tok/s

Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-5432cd

1.164,8 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

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

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91

1.090,6 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e

1.077,4 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818

1.071,0 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92

1.051,1 tok/s

gpt-oss-20b3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a

1.015,5 tok/s

Qwen3-30B-A3B-Instruct-2507 this runIntel Arc Pro B70 · run-20260810-083755-72fbc7

140,1 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA GeForce RTX 5090run-20260729-105335-2d74e4

931,7 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032122-601ed1

910,8 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-93aeaa

826,5 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-dedb22

824,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105341-2a6ebf

795,3 tok/s

NVIDIA GeForce RTX 5090run-20260723-045448-81246f

655,8 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-004604-c65af3

649,0 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-060803-1493d6

542,3 tok/s

2× NVIDIA RTX A6000run-20260829-124021-3da57d

521,6 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260724-004603-be9553

496,8 tok/s

2× NVIDIA RTX A6000run-20260827-090902-ea1289

460,0 tok/s

2× NVIDIA RTX A6000run-20260829-181041-b4b3c6

393,1 tok/s

2× NVIDIA RTX A6000run-20260827-133004-645132

362,0 tok/s

NVIDIA RTX A6000run-20260826-211812-974d8d

315,7 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

Configuration

benchmark-konfiguration — run-20260810-083755-72fbc7

# LLM-Benchmark Konfiguration # Modell : Qwen3-30B-A3B-Instruct-2507 # Engine : llama.cpp # Run-ID : run-20260810-083755-72fbc7 # 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 5

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	5
execution_type	local

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/sNVIDIA RTX A6000 758,7 tok/sAMD Radeon RX 7900 XTX 314,0 tok/sAMD Radeon PRO W7800 48GB 267,7 tok/sAMD Radeon PRO W7900 Dual Slot 264,2 tok/sAMD Radeon AI PRO R9700 240,2 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/sCPU-only 31,2 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 7955WX 16-Cores 758,7 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 314,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 267,7 tok/sAMD Ryzen 3 3100 4-Core Processor 240,2 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 218,5 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/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 314,0 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 240,2 tok/sDell Inc. PowerEdge R820 218,5 tok/sASUSTeK COMPUTER INC. GX10 169,9 tok/s★ Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 143,6 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) 107,6 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 (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 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 0.14

Token / kWh2.19M

Acquisition (system)EUR 1,378 partial priceGPU EUR 1,258 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 2,587

Output tokens (2 years)8.83B

☁️ 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 140 tok/s NVIDIA GeForce RTX 5090 932 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 911 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 827 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.