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

Generation52,73tok/s

Prefill1.821,80tok/s

Time to First Token1.334,50ms

Total duration41,51s

Concurrency1parallel

Ranking in the field

This GPU All GPUs

71of 122 systems

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

This run is better than 42 % of all comparable systems.

Generation 52,7 tok/s

-23 % vs Ø 68,2

Prefill 1.821,8 tok/s

-44 % vs Ø 3.254,3

Time to First Token 1.335 ms

-71 % vs Ø 4.539

Distribution in the field1 – 244 tok/s

Ø 68 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

Qwen3-0.6BAMD Radeon RX 7900 XTX · run-20260922-095735-545662

243,7 tok/s

Llama-3.2-1B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20260927-001710-d4b69b

209,0 tok/s

Llama-3.2-1B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20261008-105916-ae59c6

207,1 tok/s

gpt-oss-20bAMD Radeon RX 7900 XTX · run-20260922-115731-433d6d

154,9 tok/s

gpt-oss-20bAMD Radeon RX 7900 XTX · run-20260922-115731-0214a1

150,5 tok/s

Qwen3-0.6B2× 2x AMD Radeon RX 7900 XTX · run-20261008-105914-0699ab

143,4 tok/s

Llama-3.1-Nemotron-Nano-4B-v1.1AMD Radeon RX 7900 XTX · run-20260922-163818-53557b

139,3 tok/s

Qwen3-1.7B2× 2x AMD Radeon RX 7900 XTX · run-20261008-105915-12cae0

136,1 tok/s

gemma-4-E2B-itAMD Radeon RX 7900 XTX · run-20260922-115730-6b8875

133,2 tok/s

Qwen3-1.7B2× 2x AMD Radeon RX 7900 XTX · run-20260926-214312-91d307

132,3 tok/s

Qwen3-Coder-30B-A3B-InstructAMD Radeon RX 7900 XTX · run-20260922-140931-cdaee1

117,3 tok/s

Qwen3-30B-A3B-Instruct-2507AMD Radeon RX 7900 XTX · run-20260922-133638-f3fdcb

115,0 tok/s

Qwen3-30B-A3B-Thinking-2507AMD Radeon RX 7900 XTX · run-20260922-133638-425bd9

114,7 tok/s

Qwen3-Omni-30B-A3B-ThinkingAMD Radeon RX 7900 XTX · run-20260922-140931-defe2e

112,9 tok/s

Qwen3-Coder-Next this run2× 2x AMD Radeon RX 7900 XTX · run-20261009-081233-3026c6

52,7 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260728-184455-777e64

242,2 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032131-7d5f01

218,4 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032132-4c6758

216,5 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260729-032132-48634e

216,1 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-184454-459814

215,3 tok/s

2× NVIDIA RTX A6000run-20260830-082829-f969da

146,8 tok/s

2× NVIDIA RTX A6000run-20260830-015226-afb02c

133,1 tok/s

2× NVIDIA RTX A6000run-20260828-013306-f12842

132,4 tok/s

2× NVIDIA RTX A6000run-20260827-193208-1a5d4c

123,2 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165905-803b25

62,4 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165907-00b443

62,4 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165907-0fb55c

61,0 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165905-3afbfc

61,0 tok/s

2× AMD Radeon RX 7900 XTX this runrun-20261009-081233-3026c6

52,7 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-Coder-Next

Configuration

benchmark-konfiguration — run-20261009-081233-3026c6

# LLM-Benchmark Konfiguration # Modell : Qwen3-Coder-Next # Engine : llama.cpp # Run-ID : run-20261009-081233-3026c6 # 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 huihui-ai_Qwen3-Coder-Next-abliterated-IQ4_XS.gguf \ --alias Qwen3-Coder-Next \ -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-Coder-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.	huihui-ai_Qwen3-Coder-Next-abliterated-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

All benchmarks of this model To leaderboard

Model comparison

Qwen3-Coder-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

NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.253,3 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.147,5 tok/sNVIDIA RTX A6000 629,8 tok/s★ AMD Radeon RX 7900 XTX 197,7 tok/s this runNVIDIA GeForce RTX 5090 107,0 tok/sNVIDIA GeForce RTX 5070 Ti 106,1 tok/sAMD Radeon AI PRO R9700 78,7 tok/sNVIDIA GeForce RTX 3090 Ti 78,2 tok/sNVIDIA GB10 (DGX Spark) 38,5 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.253,3 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.147,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 629,8 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 197,7 tok/s this runAMD Ryzen 7 5800X3D 8-Core Processor 107,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 106,1 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 78,2 tok/sNVIDIA Grace 38,5 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.253,3 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.147,5 tok/s★ Dell Inc. PowerEdge R820 197,7 tok/s this runASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 107,0 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 106,1 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 78,2 tok/sASUSTeK COMPUTER INC. GX10 38,5 tok/s

ENGby engine

★ llama.cpp 1.253,3 tok/s this runvLLM 629,8 tok/sunbekannt 62,4 tok/s

DRVby driver

unbekannt 1.253,3 tok/sAMD 7.0.0-27-generic 62,4 tok/sNVIDIA 590.48.01 / CUDA 13.1 38,5 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 URL Reset

⚡ Electricity price EUR/kWh

⚙️ System utilization 100 %

🖥️ Acquisition EUR

🔌 Idle 35 W

⚡ TDP 749 W

☁️ External LLM (API) show

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

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 1.18

Token / kWh253.53K

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)3.33B

☁️ 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-Coder-Next2x AMD Radeon RX 7900 XTX	Qwen3-Coder-NextNVIDIA RTX PRO 6000 Blackwell Workstation Edition	Qwen3-Coder-Next3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	Qwen3-Coder-Next3x 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)	–	–	–	–

2× AMD Radeon RX 7900 XTX · this run 53 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 242 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 218 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 216 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.