Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkainclusionAI

Ling-3.0-flash

Performance benchmark · measured on 30.09.2026 16:35

Benchmark-IDrun-20260930-145235-42ea2e
Timebench 3 - Kombi (Prefill + Generation)MoE127.5BRuntime: vLLMQuantisierung: INT4
Generation343,90tok/s
Prefill9.629,40tok/s
Time to First Token1.973,00ms
Total duration33,83s
Concurrency5parallel
Ranking in the field
316of 1360 systems

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

This run is better than 77 % of all comparable systems.
Generation 343,9 tok/s
+36 % vs Ø 253,1
Prefill 9.629,4 tok/s
+77 % vs Ø 5.451,5
Time to First Token 1.973 ms
-93 % vs Ø 28.715
Distribution in the field0 – 1.349 tok/s
Ø 253 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
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
Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
Ling-3.0-flash this run2× 2x NVIDIA RTX A6000 · run-20260930-145235-42ea2e
343,9 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: 2x NVIDIA RTX A6000 · 48 GB VRAM
CPU: AMD EPYC 7203P 8-Core Processor
RAM: 252 GB
Mainboard: ASRockRack ROMED8-2T/BCM

Setup

Runtime: vLLM
Quantization: INT4
Model: Ling-3.0-flash

Configuration

benchmark-konfiguration — run-20260930-145235-42ea2e
# LLM-Benchmark Konfiguration # Modell : Ling-3.0-flash # Engine : vLLM # Run-ID : run-20260930-145235-42ea2e # GPU : 2x NVIDIA RTX A6000 # CPU : AMD EPYC 7203P 8-Core Processor # RAM : 252 GB bench@llm-benchmark:~$ vllm serve ling-3.0-flash-int4 \ --tensor-parallel-size 2 \ --max-num-seqs 12 '(2xA6000' NVLink, vLLM 'INT4)'
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
Tensor-Parallel?Anzahl GPUs, auf die JEDER einzelne Modell-Layer aufgeteilt wird (Tensor-Parallelitaet). Mehr GPUs = mehr VRAM und meist mehr Speed, aber die Anzahl der Attention-Heads muss durch diesen Wert teilbar sein (z.B. 32 Heads -> nur 1, 2, 4, 8 ... moeglich, NICHT 3).2
Max-Sequenzen?Maximale Anzahl gleichzeitig bearbeiteter Anfragen (Batch-Groesse). Hoeher = mehr Durchsatz, braucht aber mehr KV-Cache-Speicher.12
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
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

47836926115243,101.7233.4475.170Prefill (tok/s)Generation (tok/s)NVIDIA GB10 (DGX Spark) - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)NVIDIA GB10 (DGX Spar...AMD Radeon PRO W7900 Dual Slot - 165,7 tok/s Generation, 1.163 tok/s Prefill, TTFT 7.103 ms (27 Laufe)AMD Radeon PRO W7900 ...AMD Radeon AI PRO R9700 - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)AMD Radeon AI PRO R97...AMD Radeon RX 7900 XTX - 133,0 tok/s Generation, 240 tok/s Prefill, TTFT 131.640 ms (4 Laufe)AMD Radeon RX 7900 XTXNVIDIA RTX A6000 - 388,1 tok/s Generation, 4.204 tok/s Prefill, TTFT 7.648 ms (9 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
★ NVIDIA RTX A6000 388,1 tok/s this runNVIDIA GB10 (DGX Spark) 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

47836926115243,101.7233.4475.170Prefill (tok/s)Generation (tok/s)NVIDIA Grace - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)NVIDIA GraceAMD Ryzen Threadripper PRO 5975WX 32-Cores - 165,7 tok/s Generation, 1.163 tok/s Prefill, TTFT 7.103 ms (27 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 133,0 tok/s Generation, 240 tok/s Prefill, TTFT 131.640 ms (4 Laufe)AMD Ryzen Threadrippe...AMD EPYC 7203P 8-Core Processor - 388,1 tok/s Generation, 4.204 tok/s Prefill, TTFT 7.648 ms (9 Laufe) | DIESER LAUF★ AMD EPYC 7203P 8-Core...
★ AMD EPYC 7203P 8-Core Processor 388,1 tok/s this runNVIDIA 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/s

MBby mainboard

47237327417575,804.1058.21012.315Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. GX10 - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 194,7 tok/s Generation, 1.079 tok/s Prefill, TTFT 21.150 ms (37 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 Laufe)ASUSTeK COMPUTER INC....ASRockRack ROMED8-2T/BCM - 388,1 tok/s Generation, 10.088 tok/s Prefill, TTFT 1.544 ms (3 Laufe) | DIESER LAUF★ ASRockRack ROMED8-2T/...
★ ASRockRack ROMED8-2T/BCM 388,1 tok/s this runASUSTeK 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/s

ENGby engine

45438732125418804.0978.19312.290Prefill (tok/s)Generation (tok/s)llama.cpp - 253,7 tok/s Generation, 1.219 tok/s Prefill, TTFT 16.970 ms (75 Laufe)llama.cppvLLM - 388,1 tok/s Generation, 10.088 tok/s Prefill, TTFT 1.544 ms (3 Laufe) | DIESER LAUF★ vLLM
★ vLLM 388,1 tok/s this runllama.cpp 253,7 tok/s

DRVby driver

4543873212541881.1171.3411.5651.789Prefill (tok/s)Generation (tok/s)unbekannt - 388,1 tok/s Generation, 1.628 tok/s Prefill, TTFT 14.883 ms (63 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 253,7 tok/s Generation, 1.278 tok/s Prefill, TTFT 22.647 ms (15 Laufe)NVIDIA 590.48.01 / CU...
unbekannt 388,1 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 URLReset
⚡ Electricity price EUR/kWh
⚙️ System utilization 100 %
🖥️ Acquisition EUR
🔌 Idle 30 W
⚡ TDP 600 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)600 W estimated (TDP)GPU 600 W full load
Avg cost / hourEUR 0.18
Electricity / 1M tokensEUR 0.15
Token / kWh2.06M
Acquisition (system)EUR 6,180 partial priceGPU EUR 6,000 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 9,334
Output tokens (2 years)21.69B
☁️ 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-flash2x NVIDIA RTX A6000Ling-3.0-flash2x NVIDIA RTX A6000Ling-3.0-flashNVIDIA GB10 (DGX Spark)Ling-3.0-flashNVIDIA GB10 (DGX Spark)
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)––––

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.