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

Ling-3.0-flash

Performance benchmark · measured on 25.09.2026 18:08

Benchmark-IDrun-20260925-162606-50993f
Timebench 3 - Kombi (Prefill + Generation)MoE127.5BRuntime: llama.cppQuantisierung: Q4_K_M
Generation194,68tok/s
Prefill1.933,92tok/s
Time to First Token12.719,00ms
Total duration33,68s
Concurrency10parallel
Ranking in the field
788of 1296 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 10× concurrent

This run is better than 39 % of all comparable systems.
Generation 194,7 tok/s
-56 % vs Ø 438,6
Prefill 1.933,9 tok/s
-70 % vs Ø 6.489,1
Time to First Token 12.719 ms
-72 % vs Ø 45.070
Distribution in the field0 – 2.491 tok/s
Ø 439 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e28775
2.491,2 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-b37ed9
2.414,4 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9c966e
1.995,4 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-e0eafd
1.897,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-7c961d
1.890,7 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd
1.878,7 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b
1.835,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046
1.830,3 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-c6e7e0
1.819,5 tok/s
Ling-3.0-flash this run2× NVIDIA RTX A6000 · run-20260925-162606-50993f
194,7 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 10× concurrent · Generation (tok/s)

Hardware

GPU: 2x NVIDIA RTX A6000 · 48 GB VRAM
CPU: AMD EPYC 7203P 8-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Ling-3.0-flash

Configuration

benchmark-konfiguration — run-20260925-162606-50993f
# LLM-Benchmark Konfiguration # Modell : Ling-3.0-flash # Engine : llama.cpp # Run-ID : run-20260925-162606-50993f # GPU : 2x NVIDIA RTX A6000 # CPU : AMD EPYC 7203P 8-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server Ling-3.0-flash-Q4_K_M \ -ngl 99 \ -fa on \ -np 10 '(2x' A6000 NVLink, voll 'VRAM)'
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
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
faon
np10

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

30324819313883,505671.1341.702Prefill (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...Radeon RX 7900 XTX - 133,0 tok/s Generation, 240 tok/s Prefill, TTFT 131.640 ms (4 Laufe)Radeon RX 7900 XTXNVIDIA RTX A6000 - 194,7 tok/s Generation, 1.262 tok/s Prefill, TTFT 10.700 ms (6 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
NVIDIA GB10 (DGX Spark) 253,7 tok/s★ NVIDIA RTX A6000 194,7 tok/s this runAMD Radeon PRO W7900 Dual Slot 165,7 tok/sAMD Radeon AI PRO R9700 160,2 tok/sRadeon RX 7900 XTX 133,0 tok/s

CPUby processor

30324819313883,505671.1341.702Prefill (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 - 194,7 tok/s Generation, 1.262 tok/s Prefill, TTFT 10.700 ms (6 Laufe) | DIESER LAUF★ AMD EPYC 7203P 8-Core...
NVIDIA Grace 253,7 tok/s★ AMD EPYC 7203P 8-Core Processor 194,7 tok/s this runAMD 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

2982522071621169361.1411.3461.551Prefill (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 WRX90E-SAGE SE - 160,2 tok/s Generation, 1.407 tok/s Prefill, TTFT 6.543 ms (23 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) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. GX10 253,7 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 194,7 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 160,2 tok/s

ENGby engine

2792662542412281.1461.1951.2441.293Prefill (tok/s)Generation (tok/s)llama.cpp - 253,7 tok/s Generation, 1.219 tok/s Prefill, TTFT 16.970 ms (75 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 253,7 tok/s this run

DRVby driver

2912582241911581.1151.1991.2831.367Prefill (tok/s)Generation (tok/s)NVIDIA 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 - 194,7 tok/s Generation, 1.205 tok/s Prefill, TTFT 15.550 ms (60 Laufe)unbekannt
NVIDIA 590.48.01 / CUDA 13.1 253,7 tok/sunbekannt 194,7 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× 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 40 W
⚡ TDP 610 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)610 W estimated (TDP)GPU 600 + Board 10 W full load
Avg cost / hourEUR 0.18
Electricity / 1M tokensEUR 0.26
Token / kWh1.15M
Acquisition (system)EUR 6,428 partial priceGPU EUR 6,000 · RAM EUR 248 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 9,634
Output tokens (2 years)12.28B
☁️ 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 (40 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-flashNVIDIA GB10 (DGX Spark)Ling-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.