ℹ

Public note: NVIDIA GB10 (DGX Spark, 120GB Unified Memory) . Qwen3.6-35B-A3B Q4_K_M . llama.cpp b10507 native aarch64, -ngl 999, -np 12, -c 49152 (4096 Tok/Slot)

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.

Generation138,96tok/s

Prefill2.158,14tok/s

Time to First Token4.628,50ms

Total duration85,30s

Concurrency5parallel

Ranking in the field

This GPU All GPUs

845of 1510 systems

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

This run is better than 44 % of all comparable systems.

Generation 139,0 tok/s

-46 % vs Ø 256,1

Prefill 2.158,1 tok/s

-60 % vs Ø 5.434,2

Time to First Token 4.629 ms

-84 % vs Ø 29.420

Distribution in the field0 – 1.349 tok/s

Ø 256 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 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

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

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

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

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

Qwen3.6-35B-A3B this runNVIDIA GB10 (DGX Spark) · run-20261024-122724-fb0ba9

139,0 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 Workstation Editionrun-20261023-071819-2f8ed2

818,9 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032129-e6d323

812,6 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260731-071556-93a59c

745,0 tok/s

NVIDIA GeForce RTX 5090run-20260731-071557-28b20e

744,6 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260731-071555-fe8883

716,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260731-071555-191108

654,4 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260724-083000-a4b89b

596,5 tok/s

2× NVIDIA RTX A6000run-20260829-152523-4ec3e9

504,8 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-105337-539e80

472,3 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260804-052131-18f8d1

467,1 tok/s

2× NVIDIA RTX A6000run-20260827-111923-e052e1

455,0 tok/s

2× NVIDIA RTX A6000run-20260829-234040-9936d5

453,6 tok/s

2× NVIDIA RTX A6000run-20260827-175312-bb8c80

419,8 tok/s

2× NVIDIA RTX A6000run-20260828-105211-f19b88

374,2 tok/s

Hardware

GPU: NVIDIA GB10 · 128 GB VRAM
CPU: NVIDIA Grace
RAM: 120 GB
Mainboard: ASUSTeK COMPUTER INC. GX10

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Driver: NVIDIA 590.48.01 / CUDA 13.1
Model: Qwen3.6-35B-A3B

Configuration

benchmark-konfiguration — run-20261024-122724-fb0ba9

# LLM-Benchmark Konfiguration # Modell : Qwen3.6-35B-A3B # Engine : llama.cpp # Run-ID : run-20261024-122724-fb0ba9 # GPU : NVIDIA GB10 # CPU : NVIDIA Grace # RAM : 120 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/bench_models/Qwen_Qwen3.6-35B-A3B-Q4_K_M.gguf \ -ngl 999 \ -np 12 \ -c 49152

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
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.	49152
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
np	12
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	49152
execution_type	local

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 1.499,4 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/sNVIDIA RTX A6000 800,4 tok/sAMD Radeon RX 7900 XTX 450,5 tok/sNVIDIA GeForce RTX 3090 341,5 tok/sAMD Radeon PRO W7900 Dual Slot 296,2 tok/sAMD Radeon AI PRO R9700 271,4 tok/sAMD Radeon PRO W7800 48GB 235,5 tok/sNVIDIA Tesla V100 PCIe 32GB 225,9 tok/s★ NVIDIA GB10 (DGX Spark) 169,4 tok/s this runNVIDIA GeForce RTX 5070 Ti 142,9 tok/sIntel Arc Pro B70 124,5 tok/sAMD Radeon 8060S Graphics 98,3 tok/sNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU) 67,9 tok/sNVIDIA GeForce RTX 2060 27,5 tok/sCPU-only 4,3 tok/s

CPUby processor

AMD Ryzen 5 5600X 6-Core Processor 1.499,4 tok/sAMD 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 Threadripper PRO 7955WX 16-Cores 800,4 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 450,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 296,2 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 225,9 tok/sAMD Ryzen 3 3100 4-Core Processor 198,8 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 181,7 tok/s★ NVIDIA Grace 169,4 tok/s this runAMD Ryzen 9 7945HX with Radeon Graphics 124,5 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 98,3 tok/sNVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) 67,9 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 4,3 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.499,4 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.489,1 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/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 450,5 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 225,9 tok/sDell Inc. PowerEdge R820 181,7 tok/s★ ASUSTeK COMPUTER INC. GX10 169,4 tok/s this runShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 124,5 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) 98,3 tok/sASUS H7607BA 67,9 tok/s

ENGby engine

★ llama.cpp 1.499,4 tok/s this runvLLM 952,8 tok/sunbekannt 830,5 tok/s

DRVby driver

unbekannt 1.499,4 tok/s★ NVIDIA 590.48.01 / CUDA 13.1 169,4 tok/s this runIntel 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 (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 15 W

⚡ TDP 140 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)140 W estimated (TDP)GPU 140 W full load

Avg cost / hourEUR 0.042

Electricity / 1M tokensEUR 0.084

Token / kWh3.57M

Acquisition (system)EUR 5,800 partial priceGPU EUR 4,000 · RAM EUR 1,680 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 6,536

Output tokens (2 years)8.76B

☁️ 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 (15 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-A3BNVIDIA GB10 (DGX Spark)	Qwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	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)	–	–	–	–

NVIDIA GB10 (DGX Spark) · this run 139 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 819 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 813 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 745 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.