ℹ

For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.

Generation36,06tok/s

Prefill536,05tok/s

Time to First Token41.916,50ms

Total duration278,49s

Concurrency10parallel

Ranking in the field

This GPU All GPUs

10of 12 systems

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

This run is better than 18 % of all comparable systems.

Generation 36,1 tok/s

-51 % vs Ø 73,5

Prefill 536,1 tok/s

-57 % vs Ø 1.253,9

Time to First Token 41.917 ms

+86 % vs Ø 22.577

Distribution in the field17 – 132 tok/s

Ø 73 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

North-Mini-Code-1.0AMD Radeon 8060S Graphics · run-20260723-015518-753958

131,9 tok/s

Qwen3-30B-A3B-Instruct-2507AMD Radeon 8060S Graphics · run-20260723-015518-4f6b2e

107,6 tok/s

Qwen-AgentWorld-35B-A3BAMD Radeon 8060S Graphics · run-20260723-142109-66f9ec

103,8 tok/s

Nemotron-Cascade-2-30B-A3BAMD Radeon 8060S Graphics · run-20260723-142105-4bf79a

94,6 tok/s

Gemma-4-26B-A4B-itAMD Radeon 8060S Graphics · run-20260725-031733-4e4df6

76,3 tok/s

gemma-4-26B-A4B-it-assistantAMD Radeon 8060S Graphics · run-20260725-031727-c6550e

74,5 tok/s

gpt-oss-20bAMD Radeon 8060S Graphics · run-20260724-082941-665f99

74,4 tok/s

Gemma-4-26B-A4B-itAMD Radeon 8060S Graphics · run-20260725-031733-e7513a

73,7 tok/s

Ministral-3-14B-Reasoning-2512AMD Radeon 8060S Graphics · run-20260723-142059-0f740f

66,3 tok/s

Qwen3.6-27B this runAMD Radeon 8060S Graphics · run-20260723-194446-8d651c

36,1 tok/s

Mistral-Small-3.1-24B-Instruct-2503AMD Radeon 8060S Graphics · run-20260723-142100-b7b090

26,0 tok/s

OpenReasoning-Nemotron-32BAMD Radeon 8060S Graphics · run-20260723-142108-cc471c

16,5 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260729-032118-ab676a

546,9 tok/s

NVIDIA GeForce RTX 5090run-20260729-105334-2ef657

532,5 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-6bdcc2

464,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-67b150

446,8 tok/s

2× NVIDIA RTX A6000run-20260829-131336-3d4e79

431,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-105339-23669e

407,8 tok/s

2× NVIDIA RTX A6000run-20260827-094104-b4daed

387,3 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260729-032133-753de8

264,2 tok/s

NVIDIA RTX A6000run-20260826-222254-7d4a4f

233,6 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053403-2c9de1

165,4 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053403-b7a6dc

164,5 tok/s

2× NVIDIA RTX A6000run-20260828-091411-fa477f

163,0 tok/s

2× NVIDIA RTX A6000run-20260830-022528-ffdc47

161,5 tok/s

3× AMD Radeon AI PRO R9700run-20260805-053402-85c6e2

159,8 tok/s

Hardware

GPU: AMD Radeon 8060S Graphics
CPU: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
RAM: 31 GB
Mainboard: Bosgame AXB35-02 (BeyondMax Series)

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3.6-27B

Configuration

benchmark-konfiguration — run-20260723-194446-8d651c

# LLM-Benchmark Konfiguration # Modell : Qwen3.6-27B # Engine : llama.cpp # Run-ID : run-20260723-194446-8d651c # GPU : AMD Radeon 8060S Graphics # CPU : AMD RYZEN AI MAX+ 395 w/ Radeon 8060S # RAM : 31 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build-rocm/bin/llama-server \ -m /home/godcore/models/dl/Qwen3.6-27B-Q4_K_M.gguf \ --host 0.0.0.0 \ --port 8000 \ --gpu-layers 99 \ --flash-attn on \ -c 26624 \ --parallel 12

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.	26624
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.	/home/godcore/models/dl/Qwen3.6-27B-Q4_K_M.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.	99
Flash Attention?FlashAttention fuer schnellere und speichersparende Attention. Wert on/off/auto je nach Build.	on
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	26624
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.	12

All benchmarks of this model To leaderboard

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/sAMD Radeon PRO W7800 48GB 106,8 tok/sNVIDIA GeForce RTX 5070 Ti 57,2 tok/s★ AMD Radeon 8060S Graphics 36,1 tok/s this run

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 5975WX 32-Cores 106,8 tok/s★ AMD RYZEN AI MAX+ 395 w/ Radeon 8060S 36,1 tok/s this run

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 106,8 tok/s★ Bosgame AXB35-02 (BeyondMax Series) 36,1 tok/s this rununbekannt 28,8 tok/s

ENGby engine

★ llama.cpp 546,9 tok/s this runvLLM 431,7 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 (10× concurrent). Methodology →

⚙️ ConfigurationAll metrics and charts below follow these settings – based on a 24-month runtime.Save to URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 18 W

⚡ TDP 120 W

☁️ External LLM (API) show

Input €/1M Output €/1M Input per output token

Electricity0.30 EUR/kWh

Avg power (incl. idle)120 W estimated (TDP)GPU 120 W full load

Avg cost / hourEUR 0.036

Electricity / 1M tokensEUR 0.28

Token / kWh1.08M

Acquisition (system)EUR 7,054 partial priceGPU EUR 3,000 · Board EUR 3,500 · RAM EUR 434 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 7,685

Output tokens (2 years)2.27B

☁️ 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 (18 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

	Qwen3.6-27BAMD Radeon 8060S Graphics	Qwen3.6-27BNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen3.6-27BNVIDIA GeForce RTX 5090	Qwen3.6-27B3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
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)	–	–	–	–

AMD Radeon 8060S Graphics · this run 36 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 547 tok/s NVIDIA GeForce RTX 5090 533 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 464 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.