Created bymario-alka.dePowered bynoob2claw.detricoma.de
Contributed byMario AlkaQwen (Alibaba)

Qwen3.8-Flash-Next

Performance benchmark · measured on 14.10.2026 09:25

Benchmark-IDrun-20261014-073140-ec35cc
Timebench 3 - Kombi (Prefill + Generation)MoE180BRuntime: llama.cppQuantisierung: UD-Q4_K_XL
Generation79,19tok/s
Prefill669,56tok/s
Time to First Token33.965,00ms
Total duration328,95s
Concurrency10parallel
Ranking in the field
335of 343 systems

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

This run is better than 2 % of all comparable systems.
Generation 79,2 tok/s
-80 % vs Ø 405,1
Prefill 669,6 tok/s
-94 % vs Ø 11.456,2
Time to First Token 33.965 ms
+210 % vs Ø 10.949
Distribution in the field26 – 1.568 tok/s
Ø 405 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

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: 126 GB
Mainboard: ASRockRack ROMED8-2T/BCM

Setup

Runtime: llama.cpp
Quantization: UD-Q4_K_XL
Model: Qwen3.8-Flash-Next

Configuration

benchmark-konfiguration — run-20261014-073140-ec35cc
# LLM-Benchmark Konfiguration # Modell : Qwen3.8-Flash-Next # Engine : llama.cpp # Run-ID : run-20261014-073140-ec35cc # GPU : 2x NVIDIA RTX A6000 # CPU : AMD EPYC 7203P 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ llama-server \ --model /home/godcore/models/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf \ --n-cpu-moe 10 \ -ngl 99 \ -np 10 \ -c 40960
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.Qwen3.8-Flash-Next
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.40960
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/models/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
n-cpu-moe10
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
np10
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.40960
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Qwen3.8-Flash-Next 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

2.0301.5231.0155080,005.46510.93016.395Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.564,6 tok/s Generation, 6.065 tok/s Prefill, TTFT 7.635 ms (15 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 - 1.132,7 tok/s Generation, 1.949 tok/s Prefill, TTFT 28.686 ms (12 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 584,1 tok/s Generation, 13.248 tok/s Prefill, TTFT 766 ms (8 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA DGX SPARK (GB10) - 492,8 tok/s Generation, 1.262 tok/s Prefill, TTFT 33.373 ms (12 Laufe)NVIDIA DGX SPARK (GB1...NVIDIA GeForce RTX 5090 - 346,0 tok/s Generation, 4.624 tok/s Prefill, TTFT 3.382 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA Tesla V100 PCIe 32GB - 196,2 tok/s Generation, 775 tok/s Prefill, TTFT 30.834 ms (8 Laufe)NVIDIA Tesla V100 PCI...AMD Radeon RX 7900 XTX - 18,7 tok/s Generation, 180 tok/s Prefill, TTFT 55.956 ms (3 Laufe)AMD Radeon RX 7900 XTXNVIDIA RTX A6000 - 1.171,8 tok/s Generation, 963 tok/s Prefill, TTFT 32.556 ms (21 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.564,6 tok/s★ NVIDIA RTX A6000 1.171,8 tok/s this runNVIDIA GeForce RTX 3090 1.132,7 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 584,1 tok/sNVIDIA DGX SPARK (GB10) 492,8 tok/sNVIDIA GeForce RTX 5090 346,0 tok/sNVIDIA Tesla V100 PCIe 32GB 196,2 tok/sAMD Radeon RX 7900 XTX 18,7 tok/s

CPUby processor

2.0301.5231.0155080,005.47610.95216.428Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 7945HX with Radeon Graphics - 1.564,6 tok/s Generation, 2.312 tok/s Prefill, TTFT 17.248 ms (6 Laufe)AMD Ryzen 9 7945HX wi...AMD Ryzen Threadripper PRO 3945WX 12-Cores - 1.171,8 tok/s Generation, 2.569 tok/s Prefill, TTFT 15.123 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 5 5600X 6-Core Processor - 1.132,7 tok/s Generation, 4.274 tok/s Prefill, TTFT 23.110 ms (15 Laufe)AMD Ryzen 5 5600X 6-C...AMD Ryzen 9 9950X 16-Core Processor - 584,1 tok/s Generation, 13.248 tok/s Prefill, TTFT 766 ms (8 Laufe)AMD Ryzen 9 9950X 16-...NVIDIA Grace - 492,8 tok/s Generation, 1.262 tok/s Prefill, TTFT 33.373 ms (12 Laufe)NVIDIA GraceAMD Ryzen Threadripper PRO 9965WX 24-Cores - 424,2 tok/s Generation, 0 tok/s Prefill, TTFT 1.438 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 346,0 tok/s Generation, 4.624 tok/s Prefill, TTFT 3.382 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics - 196,2 tok/s Generation, 757 tok/s Prefill, TTFT 36.737 ms (5 Laufe)AMD Ryzen 3 PRO 3200G...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 63,2 tok/s Generation, 803 tok/s Prefill, TTFT 20.996 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 18,7 tok/s Generation, 180 tok/s Prefill, TTFT 55.956 ms (3 Laufe)AMD Ryzen Threadrippe...AMD EPYC 7203P 8-Core Processor - 79,2 tok/s Generation, 320 tok/s Prefill, TTFT 39.530 ms (15 Laufe) | DIESER LAUF★ AMD EPYC 7203P 8-Core...
AMD Ryzen 9 7945HX with Radeon Graphics 1.564,6 tok/sAMD Ryzen Threadripper PRO 3945WX 12-Cores 1.171,8 tok/sAMD Ryzen 5 5600X 6-Core Processor 1.132,7 tok/sAMD Ryzen 9 9950X 16-Core Processor 584,1 tok/sNVIDIA Grace 492,8 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 424,2 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 346,0 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 196,2 tok/s★ AMD EPYC 7203P 8-Core Processor 79,2 tok/s this runIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 63,2 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 18,7 tok/s

MBby mainboard

2.0271.5201.0135070,005.47610.95216.428Prefill (tok/s)Generation (tok/s)Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) - 1.564,6 tok/s Generation, 2.312 tok/s Prefill, TTFT 17.248 ms (6 Laufe)Shenzhen Meigao Elect...unbekannt - 1.171,8 tok/s Generation, 2.569 tok/s Prefill, TTFT 15.123 ms (6 Laufe)unbekanntASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.132,7 tok/s Generation, 4.332 tok/s Prefill, TTFT 19.822 ms (18 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 584,1 tok/s Generation, 13.248 tok/s Prefill, TTFT 766 ms (8 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. GX10 - 492,8 tok/s Generation, 1.262 tok/s Prefill, TTFT 33.373 ms (12 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 424,2 tok/s Generation, 0 tok/s Prefill, TTFT 1.438 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 196,2 tok/s Generation, 757 tok/s Prefill, TTFT 36.737 ms (5 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 63,2 tok/s Generation, 803 tok/s Prefill, TTFT 20.996 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 35,4 tok/s Generation, 170 tok/s Prefill, TTFT 59.933 ms (9 Laufe)ASUSTeK COMPUTER INC....ASRockRack ROMED8-2T/BCM - 79,2 tok/s Generation, 423 tok/s Prefill, TTFT 24.603 ms (9 Laufe) | DIESER LAUF★ ASRockRack ROMED8-2T/...
Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 1.564,6 tok/sunbekannt 1.171,8 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.132,7 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 584,1 tok/sASUSTeK COMPUTER INC. GX10 492,8 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 424,2 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 196,2 tok/s★ ASRockRack ROMED8-2T/BCM 79,2 tok/s this runDell Inc. PowerEdge R820 63,2 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 35,4 tok/s

ENGby engine

1.9651.4749834910,005.02910.05815.087Prefill (tok/s)Generation (tok/s)strata - 1.564,6 tok/s Generation, 1.819 tok/s Prefill, TTFT 32.559 ms (29 Laufe)strataunbekannt - 1.171,8 tok/s Generation, 1.981 tok/s Prefill, TTFT 17.080 ms (9 Laufe)unbekanntvLLM - 584,1 tok/s Generation, 10.429 tok/s Prefill, TTFT 1.500 ms (17 Laufe)vLLMtensorfold - 344,4 tok/s Generation, 12.258 tok/s Prefill, TTFT 1.105 ms (3 Laufe)tensorfoldllama.cpp - 1.555,3 tok/s Generation, 627 tok/s Prefill, TTFT 35.323 ms (24 Laufe) | DIESER LAUF★ llama.cpp
strata 1.564,6 tok/s★ llama.cpp 1.555,3 tok/s this rununbekannt 1.171,8 tok/svLLM 584,1 tok/stensorfold 344,4 tok/s

DRVby driver

1.9351.4821.0295751226831.7682.8523.936Prefill (tok/s)Generation (tok/s)unbekannt - 1.564,6 tok/s Generation, 3.358 tok/s Prefill, TTFT 22.790 ms (70 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 492,8 tok/s Generation, 1.262 tok/s Prefill, TTFT 33.373 ms (12 Laufe)NVIDIA 590.48.01 / CU...
unbekannt 1.564,6 tok/sNVIDIA 590.48.01 / CUDA 13.1 492,8 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 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 0.63
Token / kWh475.14K
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)4.99B
☁️ 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

Qwen3.8-Flash-Next2x NVIDIA RTX A6000Qwen3.8-Flash-NextNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionQwen3.8-Flash-NextNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionQwen3.8-Flash-NextNVIDIA 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)––––

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.