Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaQwen (Alibaba)

Qwen3.8-Flash-Next

Performance benchmark · measured on 29.09.2026 10:49

Benchmark-IDrun-20260929-091306-2dbc7d
Timebench 3 - Kombi (Prefill + Generation)MoE180BRuntime: llama.cppQuantisierung: UD-Q4_K_XL
Generation9,85tok/s
Prefill114,12tok/s
Time to First Token19.280,00ms
Total duration157,46s
Concurrency1parallel
Ranking in the field
110of 119 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 8 % of all comparable systems.
Generation 9,9 tok/s
-85 % vs Ø 67,8
Prefill 114,1 tok/s
-96 % vs Ø 3.244,0
Time to First Token 19.280 ms
+316 % vs Ø 4.629
Distribution in the field1 – 244 tok/s
Ø 68 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× concurrent · Generation (tok/s)

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: AMD Ryzen Threadripper PRO 3955WX 16-Cores
RAM: 189 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

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

Configuration

benchmark-konfiguration — run-20260929-091306-2dbc7d
# LLM-Benchmark Konfiguration # Modell : Qwen3.8-Flash-Next # Engine : llama.cpp # Run-ID : run-20260929-091306-2dbc7d # GPU : 2x AMD Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 189 GB bench@llm-benchmark:~$ llama-server Qwen3.8-Flash-Next-UD-Q4_K_XL \ -ngl 999 \ --n-cpu-moe 99 \ -c 24576 \ -np 10 '(2x' RX 7900 XTX + 196GB RAM 'Offload)'
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
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.24576
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
n-cpu-moe99
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.24576
np10
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

2.0301.5231.0155080,009451.8902.835Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.564,6 tok/s Generation, 2.312 tok/s Prefill, TTFT 17.248 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 Laufe)NVIDIA GeForce RTX 30...NVIDIA GB10 (DGX Spark) - 492,8 tok/s Generation, 1.262 tok/s Prefill, TTFT 33.373 ms (12 Laufe)NVIDIA GB10 (DGX Spar...NVIDIA RTX A6000 - 79,2 tok/s Generation, 320 tok/s Prefill, TTFT 39.530 ms (15 Laufe)NVIDIA RTX A6000AMD Radeon RX 7900 XTX - 18,7 tok/s Generation, 180 tok/s Prefill, TTFT 55.956 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.564,6 tok/sNVIDIA GeForce RTX 3090 1.132,7 tok/sNVIDIA GB10 (DGX Spark) 492,8 tok/sNVIDIA RTX A6000 79,2 tok/s★ AMD Radeon RX 7900 XTX 18,7 tok/s this run

CPUby processor

2.0301.5231.0155080,009451.8902.835Prefill (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 5 5600X 6-Core Processor - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 Laufe)AMD Ryzen 5 5600X 6-C...10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 - 492,8 tok/s Generation, 1.262 tok/s Prefill, TTFT 33.373 ms (12 Laufe)10 x ARM implementer ...AMD EPYC 7203P 8-Core Processor - 79,2 tok/s Generation, 320 tok/s Prefill, TTFT 39.530 ms (15 Laufe)AMD EPYC 7203P 8-Core...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 18,7 tok/s Generation, 180 tok/s Prefill, TTFT 55.956 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 7945HX with Radeon Graphics 1.564,6 tok/sAMD Ryzen 5 5600X 6-Core Processor 1.132,7 tok/s10 x ARM implementer 0x41, part 0xd87 + 10 x ARM implementer 0x41, part 0xd85 492,8 tok/sAMD EPYC 7203P 8-Core Processor 79,2 tok/s★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 18,7 tok/s this run

MBby mainboard

2.0271.5201.0135070,009451.8912.836Prefill (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...ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.132,7 tok/s Generation, 968 tok/s Prefill, TTFT 51.682 ms (6 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....ASRockRack ROMED8-2T/BCM - 79,2 tok/s Generation, 423 tok/s Prefill, TTFT 24.603 ms (9 Laufe)ASRockRack ROMED8-2T/...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 35,4 tok/s Generation, 170 tok/s Prefill, TTFT 59.933 ms (9 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 1.564,6 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.132,7 tok/sASUSTeK COMPUTER INC. GX10 492,8 tok/sASRockRack ROMED8-2T/BCM 79,2 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 35,4 tok/s this run

ENGby engine

2.0101.5071.0055020,01311.0992.0663.034Prefill (tok/s)Generation (tok/s)strata - 1.564,6 tok/s Generation, 1.167 tok/s Prefill, TTFT 47.749 ms (15 Laufe)stratavLLM - 122,4 tok/s Generation, 2.538 tok/s Prefill, TTFT 3.634 ms (3 Laufe)vLLMllama.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 runvLLM 122,4 tok/s

DRVby driver

1.7211.6431.5651.4861.4088999379751.014Prefill (tok/s)Generation (tok/s)unbekannt - 1.564,6 tok/s Generation, 956 tok/s Prefill, TTFT 37.497 ms (42 Laufe)unbekannt
unbekannt 1.564,6 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× 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 10 W
⚡ TDP 720 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)720 W estimated (TDP)GPU 710 + Board 10 W full load
Avg cost / hourEUR 0.22
Electricity / 1M tokensEUR 6.09
Token / kWh49.25K
Acquisition (system)EUR 3,790 partial priceGPU EUR 2,098 · RAM EUR 1,512 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 7,574
Output tokens (2 years)621.26M
☁️ 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 (10 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 AMD Radeon RX 7900 XTXQwen3.8-Flash-NextNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionQwen3.8-Flash-NextNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionQwen3.8-Flash-NextNVIDIA GeForce RTX 3090
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.