Contributed byMario AlkaQwen (Alibaba) Qwen3.6-27B
Performance benchmark · measured on 08.10.2026 10:49
Benchmark-ID
run-20261009-081230-5d75f0Timebench 3 - Kombi (Prefill + Generation)Dense27BRuntime: llama.cppQuantisierung: Q4_K_M
ℹ
Public note: Dell PowerEdge R820 . 2x AMD Radeon RX 7900 XTX (48 GB VRAM gesamt, ROCm/HIP) . RAM: 32x 16 GB SK Hynix DDR3-1600 ECC RDIMM (HMT42GR7AFR4A-PB) = 512 GB @ 1600 MT/s
Generation76,06tok/s
Prefill1.169,61tok/s
Time to First Token8.754,50ms
Total duration165,75s
Concurrency5parallel
Ranking in the field
1054of 1469 systems
Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent
This run is better than 28 % of all comparable systems.
Generation
76,1 tok/s
-69 % vs Ø 246,5
Prefill
1.169,6 tok/s
-78 % vs Ø 5.365,8
Time to First Token
8.755 ms
-71 % vs Ø 30.155
Distribution in the field0 – 1.349 tok/s
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
Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-b22926
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
Qwen3.6-27B this run2× 2x AMD Radeon RX 7900 XTX · run-20261009-081230-5d75f0
76,1 tok/s
How does this benchmark compare on other GPUs?
Same model on different hardware · 5× concurrent · Generation (tok/s)
NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032118-d71246
288,0 tok/s
NVIDIA GeForce RTX 5090run-20260729-105334-6ff273
282,1 tok/s
2× NVIDIA RTX A6000run-20260829-131336-2aa474
252,4 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-68e193
247,5 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-346cca
245,8 tok/s
2× NVIDIA RTX A6000run-20260827-094104-2ce804
232,0 tok/s
3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-583d9f
216,3 tok/s
NVIDIA GeForce RTX 3090 Tirun-20260729-032133-d19065
142,7 tok/s
NVIDIA RTX A6000run-20260826-222254-a4f59d
140,7 tok/s
3× AMD Radeon AI PRO R9700run-20260805-053402-f805f0
86,4 tok/s
3× AMD Radeon AI PRO R9700run-20260805-053403-509127
86,4 tok/s
3× AMD Radeon AI PRO R9700run-20260805-053402-a3a4f5
84,3 tok/s
2× NVIDIA RTX A6000run-20260828-091411-f27d67
83,7 tok/s
2× NVIDIA RTX A6000run-20260830-022528-74c202
83,3 tok/s
Hardware
GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820
Setup
Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3.6-27B
Configuration
# LLM-Benchmark Konfiguration
# Modell : Qwen3.6-27B
# Engine : llama.cpp
# Run-ID : run-20261009-081230-5d75f0
# GPU : 2x AMD Radeon RX 7900 XTX
# CPU : 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz
# RAM : 504 GB
bench@llm-benchmark:~$ llama-server \
-m Qwen3.6-27B-IQ4_XS.gguf \
--alias Qwen3.6-27B \
-ngl 999 \
-sm layer \
-fa on \
-c 40960 \
-np 10 '(2x' RX 7900 XTX ROCm/HIP, 'gpu)'
| 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. | Qwen3.6-27B |
| 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. | Qwen3.6-27B-IQ4_XS.gguf |
| 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 |
| Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise). | layer |
| fa | on |
| Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells. | 40960 |
| np | 10 |
| execution_type | local |
Anzeige
Model comparison
Qwen3.6-27B 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
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 546,9 tok/sNVIDIA GeForce RTX 5090 532,5 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 464,1 tok/sNVIDIA RTX A6000 431,7 tok/sNVIDIA GeForce RTX 3090 Ti 264,2 tok/sAMD Radeon AI PRO R9700 165,4 tok/s★ AMD Radeon RX 7900 XTX 110,0 tok/s this runAMD Radeon PRO W7800 48GB 106,8 tok/sNVIDIA GeForce RTX 5070 Ti 57,2 tok/sAMD Radeon 8060S Graphics 36,1 tok/s
CPUby processor
AMD Ryzen 9 9950X 16-Core Processor 546,9 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 532,5 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 464,1 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 431,7 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 264,2 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 110,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 106,8 tok/sAMD Ryzen 3 3100 4-Core Processor 99,7 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 95,6 tok/s this runAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 36,1 tok/s
MBby mainboard
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 546,9 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 532,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 464,1 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 264,2 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 110,0 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 99,7 tok/s★ Dell Inc. PowerEdge R820 95,6 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) 36,1 tok/sunbekannt 28,8 tok/s
DRVby driver
unbekannt 546,9 tok/sNVIDIA 580.159.03 / CUDA 13.0 28,8 tok/s
💰 Economics
Economics of this run
Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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
35 W
⚡ TDP
749 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)749 W estimated (TDP)GPU 710 + CPU 29 + Board 10 W full load
Avg cost / hourEUR 0.22
Electricity / 1M tokensEUR 0.82
Token / kWh365.70K
Acquisition (system)EUR 4,353 partial priceGPU EUR 2,098 · CPU EUR 59 · RAM EUR 2,016 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 8,288
Output tokens (2 years)4.80B
☁️ 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 (35 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
| Qwen3.6-27B2x AMD Radeon RX 7900 XTX | Qwen3.6-27BNVIDIA RTX PRO 6000 Blackwell Workstation Edition | Qwen3.6-27BNVIDIA GeForce RTX 5090 | Qwen3.6-27B2x NVIDIA 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) | – | – | – | – |
2× AMD Radeon RX 7900 XTX · this run 76 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 288 tok/sNVIDIA GeForce RTX 5090 282 tok/s2× NVIDIA RTX A6000 252 tok/s
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.