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

Qwen3.8-27B

Performance benchmark · measured on 27.08.2026 00:06

Benchmark-IDrun-20260826-222255-4fdb21
Timebench 3 - Kombi (Prefill + Generation)Qwen3_5ForConditionalGeneration (multimodal, image-text-to-text)27BRuntime: vLLMQuantisierung: INT4
Generation32,45tok/s
Prefill1.725,75tok/s
Time to First Token1.144,00ms
Total duration65,40s
Concurrency1parallel
Ranking in the field
710of 1264 systems

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

This run is better than 44 % of all comparable systems.
Generation 32,5 tok/s
-57 % vs Ø 75,6
Prefill 1.725,8 tok/s
-31 % vs Ø 2.498,4
Time to First Token 1.144 ms
-97 % vs Ø 32.833
Distribution in the field0 – 405 tok/s
Ø 76 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: NVIDIA RTX A6000 · 48 GB VRAM
CPU: AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: vLLM
Quantization: INT4
Model: Qwen3.8-27B

Configuration

benchmark-konfiguration — run-20260826-222255-4fdb21
# LLM-Benchmark Konfiguration # Modell : Qwen3.8-27B # Engine : vLLM # Run-ID : run-20260826-222255-4fdb21 # GPU : NVIDIA RTX A6000 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ vllm serve \ --model Qwen3.8-27B
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.Qwen3.8-27B

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Qwen3.8-27B 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

2552432302182061.9872.2462.5052.764Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 229,4 tok/s Generation, 2.202 tok/s Prefill, TTFT 2.623 ms (36 Laufe)AMD Radeon AI PRO R97...NVIDIA RTX A6000 - 231,5 tok/s Generation, 2.548 tok/s Prefill, TTFT 4.306 ms (3 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
★ NVIDIA RTX A6000 231,5 tok/s this runAMD Radeon AI PRO R9700 229,4 tok/s

CPUby processor

2552432322202082.0952.1842.2742.363Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 231,5 tok/s Generation, 2.229 tok/s Prefill, TTFT 2.753 ms (39 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 231,5 tok/s this run

MBby mainboard

2552432322202082.0952.1842.2742.363Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 231,5 tok/s Generation, 2.229 tok/s Prefill, TTFT 2.753 ms (39 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 231,5 tok/s this run

ENGby engine

28022416911458,91.3962.0412.6853.330Prefill (tok/s)Generation (tok/s)llama.cpp - 107,0 tok/s Generation, 1.782 tok/s Prefill, TTFT 1.546 ms (24 Laufe)llama.cppvLLM - 231,5 tok/s Generation, 2.944 tok/s Prefill, TTFT 4.683 ms (15 Laufe) | DIESER LAUF★ vLLM
★ vLLM 231,5 tok/s this runllama.cpp 107,0 tok/s

DRVby driver

2552432322202082.0952.1842.2742.363Prefill (tok/s)Generation (tok/s)unbekannt - 231,5 tok/s Generation, 2.229 tok/s Prefill, TTFT 2.753 ms (39 Laufe)unbekannt
unbekannt 231,5 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 65 W
⚡ TDP 71 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)71 W missingCPU 46 + Board 25 W full load
Avg cost / hourEUR 0.021
Electricity / 1M tokensEUR 0.18
Token / kWh1.65M
Acquisition (system)EUR 8,394 full priceGPU EUR 3,000 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 120
Electricity (2 years)
TCO (2 years)EUR 8,767
Output tokens (2 years)2.05B
☁️ External LLM (API) – comparison
External LLM cost (2 years)
Savings vs. external (2 years)
No power draw measured – values estimated from GPU TDP + CPU (idle + 15 %) + board.

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 (65 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

Qwen3.8-27BNVIDIA RTX A6000Qwen3.8-27B4x AMD Radeon AI PRO R9700Qwen3.8-27BAMD Radeon AI PRO R9700Qwen3.8-27BAMD Radeon AI PRO R9700
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.