ℹ

Public note: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB . Ling-3.0-flash NVFP4 (4-Bit, compressed-tensors nvfp4-pack-quantized, Gruppe 16) . vLLM 0.32.0, MARLIN NvFp4-MoE-Backend, TRITON_MLA Attention, max-model-len 8192, max-num-seqs 12, gpu-memory-utilization 0.93

⚠

Configuration note: Es sind 2 Grafikkarten installiert, aber nur 1 wurde fuer diesen Lauf genutzt. Mit allen 2 GPUs koennte der Durchsatz deutlich hoeher liegen.

Generation417,52tok/s

Prefill12.747,32tok/s

Time to First Token958,50ms

Total duration26,46s

Concurrency5parallel

Ranking in the field

This GPU All GPUs

301of 1512 systems

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

This run is better than 80 % of all comparable systems.

Generation 417,5 tok/s

+63 % vs Ø 256,0

Prefill 12.747,3 tok/s

+135 % vs Ø 5.429,9

Time to First Token 959 ms

-97 % vs Ø 29.391

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

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

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

1.090,6 tok/s

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

1.077,4 tok/s

Ling-3.0-flash this runNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20261024-140625-e1036d

417,5 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 Edition this runrun-20261024-140625-e1036d

417,5 tok/s

2× NVIDIA RTX A6000run-20260930-145235-42ea2e

343,9 tok/s

2× NVIDIA RTX A6000run-20261001-120303-dcc8f0

190,5 tok/s

2× NVIDIA RTX A6000run-20261001-081040-aff406

190,1 tok/s

2× NVIDIA RTX A6000run-20260925-162606-8b7351

184,8 tok/s

NVIDIA DGX SPARK (GB10)run-20260820-173706-3b8d9a

142,8 tok/s

NVIDIA DGX SPARK (GB10)run-20260820-131510-106a01

140,4 tok/s

NVIDIA DGX SPARK (GB10)run-20260820-131510-86a354

139,8 tok/s

4× AMD Radeon AI PRO R9700run-20260820-050509-a93a3e

131,4 tok/s

2× AMD Radeon PRO W7900 Dual Slotrun-20260820-061102-a8023a

130,6 tok/s

2× AMD Radeon PRO W7900 Dual Slotrun-20260820-050509-8942fa

129,9 tok/s

4× AMD Radeon AI PRO R9700run-20260820-035952-212f92

125,3 tok/s

2× AMD Radeon PRO W7900 Dual Slotrun-20260820-035952-691c87

119,8 tok/s

4× AMD Radeon AI PRO R9700run-20260818-060834-a804d9

98,8 tok/s

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen 9 7945HX with Radeon Graphics
RAM: 60 GB
Mainboard: Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series)

Setup

Runtime: vLLM
Quantization: NVFP4
Model: Ling-3.0-flash

Configuration

benchmark-konfiguration — run-20261024-140625-e1036d

# LLM-Benchmark Konfiguration # Modell : Ling-3.0-flash # Engine : vLLM # Run-ID : run-20261024-140625-e1036d # GPU : NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen 9 7945HX with Radeon Graphics # RAM : 60 GB bench@llm-benchmark:~$ /usr/bin/python3 /usr/local/bin/vllm serve /model \ --served-model-name Ling-3.0-flash \ --trust-remote-code \ --max-model-len 8192 \ --max-num-seqs 12 \ --gpu-memory-utilization 0.93 \ --port 8000 \ --host 0.0.0.0

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.	Ling-3.0-flash
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.	Ling-3.0-flash
Trust-Remote-Code?Erlaubt vLLM, mit dem Modell mitgelieferten Python-Code auszufuehren. Noetig fuer Architekturen, die vLLM nicht von Haus aus kennt. Nur bei vertrauenswuerdigen Modellen aktivieren.	aktiv
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	8192
Max-Sequenzen?Maximale Anzahl gleichzeitig bearbeiteter Anfragen (Batch-Groesse). Hoeher = mehr Durchsatz, braucht aber mehr KV-Cache-Speicher.	12
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'.	0.93
execution_type	local

All benchmarks of this model To leaderboard

Model comparison

Ling-3.0-flash 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 697,4 tok/s this runNVIDIA RTX A6000 388,1 tok/sNVIDIA DGX SPARK (GB10) 253,7 tok/sAMD Radeon PRO W7900 Dual Slot 165,7 tok/sAMD Radeon AI PRO R9700 160,2 tok/sAMD Radeon RX 7900 XTX 133,0 tok/s

CPUby processor

★ AMD Ryzen 9 7945HX with Radeon Graphics 697,4 tok/s this runAMD EPYC 7203P 8-Core Processor 388,1 tok/sNVIDIA Grace 253,7 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 165,7 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 160,2 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 133,0 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 14,9 tok/s

MBby mainboard

★ Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 697,4 tok/s this runASRockRack ROMED8-2T/BCM 388,1 tok/sASUSTeK COMPUTER INC. GX10 253,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 194,7 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 160,2 tok/sDell Inc. PowerEdge R820 14,9 tok/s

ENGby engine

★ vLLM 697,4 tok/s this runllama.cpp 253,7 tok/s

DRVby driver

unbekannt 697,4 tok/sNVIDIA 590.48.01 / CUDA 13.1 253,7 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 30 W

⚡ TDP 300 W

☁️ External LLM (API) show

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

Electricity0.30 EUR/kWh

Avg power (incl. idle)300 W estimated (TDP)GPU 300 W full load

Avg cost / hourEUR 0.090

Electricity / 1M tokensEUR 0.060

Token / kWh5.01M

Acquisition (system)EUR 13,120 partial priceGPU EUR 13,000 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 14,697

Output tokens (2 years)26.33B

☁️ 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 (30 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

	Ling-3.0-flashNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Ling-3.0-flash2x NVIDIA RTX A6000	Ling-3.0-flash2x NVIDIA RTX A6000	Ling-3.0-flash2x NVIDIA 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 RTX PRO 6000 Blackwell Max-Q Workstation Edition · this run 418 tok/s 2× NVIDIA RTX A6000 344 tok/s 2× NVIDIA RTX A6000 190 tok/s 2× NVIDIA RTX A6000 190 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.