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

Generation68,34tok/s

Prefill3.961,29tok/s

Time to First Token5.236,00ms

Total duration310,95s

Concurrency10parallel

Ranking in the field

This GPU All GPUs

107of 119 systems

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

This run is better than 10 % of all comparable systems.

Generation 68,3 tok/s

-72 % vs Ø 246,2

Prefill 3.961,3 tok/s

-50 % vs Ø 7.915,5

Time to First Token 5.236 ms

-84 % vs Ø 33.707

Distribution in the field0 – 718 tok/s

Ø 246 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

Llama-3.2-1B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20260927-015653-08deac

717,6 tok/s

Llama-3.2-1B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20260927-001710-43cae4

696,8 tok/s

Llama-3.2-1B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20261008-105916-a4198f

609,5 tok/s

SmolLM2-1.7B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20260927-023029-102f1c

531,7 tok/s

Qwen3-0.6B2× 2x AMD Radeon RX 7900 XTX · run-20261008-105914-7362f8

480,5 tok/s

Laguna-XS-2.1AMD Radeon RX 7900 XTX · run-20260922-123035-7c2c68

468,6 tok/s

Llama-3.2-3B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20260927-015653-e563bf

465,7 tok/s

gemma-4-E2B-it same modelAMD Radeon RX 7900 XTX · run-20260922-115730-2d5902

465,5 tok/s

gemma-4-E2B-it same modelAMD Radeon RX 7900 XTX · run-20260922-115730-03c274

455,4 tok/s

Qwen-AgentWorld-35B-A3BAMD Radeon RX 7900 XTX · run-20260922-144315-669fca

451,0 tok/s

Qwen3.6-35B-A3BAMD Radeon RX 7900 XTX · run-20260922-140931-3239aa

450,5 tok/s

Qwen3.5-35B-A3BAMD Radeon RX 7900 XTX · run-20260922-133638-2aaab2

447,0 tok/s

Qwen3-1.7B2× 2x AMD Radeon RX 7900 XTX · run-20260926-214312-7124bb

445,2 tok/s

Qwen2.5-7B-Instruct2× 2x AMD Radeon RX 7900 XTX · run-20260926-171705-51cd01

442,0 tok/s

gemma-4-E2B-it this run2× 2x AMD Radeon RX 7900 XTX · run-20261008-105920-9af9bb

68,3 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA GeForce RTX 5090run-20260728-184455-e28775

2.491,2 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260727-181606-b37ed9

2.414,4 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-184456-d87c73

2.143,6 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260728-140953-875f2e

1.744,0 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-090152-d5613d

1.743,1 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-032758-bb6a92

1.608,5 tok/s

2× NVIDIA RTX A6000run-20260829-102814-5fd238

1.568,0 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260727-142111-067e7e

1.492,8 tok/s

2× NVIDIA RTX A6000run-20260827-073158-73b96c

1.359,1 tok/s

NVIDIA RTX A6000run-20260826-190954-c9d261

1.122,5 tok/s

NVIDIA GB10run-20260729-224611-cc3776

903,3 tok/s

NVIDIA GB10run-20260729-224610-32ded2

860,9 tok/s

Intel Arc Pro B70run-20260729-224611-0989d2

826,2 tok/s

AMD Radeon PRO W7800 48GBrun-20260828-123128-d94027

702,9 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: gemma-4-E2B-it

Configuration

benchmark-konfiguration — run-20261008-105920-9af9bb

# LLM-Benchmark Konfiguration # Modell : gemma-4-E2B-it # Engine : llama.cpp # Run-ID : run-20261008-105920-9af9bb # 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 google_gemma-4-E2B-it-IQ4_XS.gguf \ --alias gemma-4-E2B-it \ -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.	gemma-4-E2B-it
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.	google_gemma-4-E2B-it-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

gemma-4-E2B-it 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 GeForce RTX 5090 2.491,2 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 2.414,4 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 2.143,6 tok/sNVIDIA GeForce RTX 5070 Ti 1.744,0 tok/sNVIDIA RTX A6000 1.568,0 tok/sNVIDIA GeForce RTX 3090 Ti 1.492,8 tok/sNVIDIA GB10 (DGX Spark) 903,3 tok/sIntel Arc Pro B70 826,2 tok/sAMD Radeon PRO W7800 48GB 702,9 tok/s★ AMD Radeon RX 7900 XTX 465,5 tok/s this runAMD Radeon AI PRO R9700 427,8 tok/sNVIDIA Tesla V100 PCIe 32GB 361,8 tok/sNVIDIA GeForce RTX 2060 54,7 tok/s

CPUby processor

AMD Ryzen 7 5800X3D 8-Core Processor 2.491,2 tok/sAMD Ryzen 9 9950X 16-Core Processor 2.414,4 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 2.143,6 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 1.744,0 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 1.568,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 1.492,8 tok/sNVIDIA Grace 903,3 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 826,2 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 465,5 tok/sAMD Ryzen 5 5600X 6-Core Processor 451,1 tok/sAMD Ryzen 3 3100 4-Core Processor 427,8 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 361,8 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 68,3 tok/s this runIntel(R) Core(TM) i5-7400 CPU @ 3.00GHz 15,3 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 2.491,2 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 2.414,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 2.143,6 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1.744,0 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 1.492,8 tok/sASUSTeK COMPUTER INC. GX10 903,3 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 826,2 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 451,1 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 427,8 tok/s★ Dell Inc. PowerEdge R820 68,3 tok/s this runASRock H110 Pro BTC+ 15,3 tok/s

ENGby engine

★ llama.cpp 2.491,2 tok/s this runvLLM 1.608,5 tok/s

DRVby driver

unbekannt 2.491,2 tok/sNVIDIA 590.48.01 / CUDA 13.1 903,3 tok/sIntel 26.18.38308.4 826,2 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 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 0.91

Token / kWh328.58K

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)4.31B

☁️ 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

	gemma-4-E2B-it2x AMD Radeon RX 7900 XTX	gemma-4-E2B-itNVIDIA GeForce RTX 5090	gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gemma-4-E2B-it3x 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 68 tok/s NVIDIA GeForce RTX 5090 2,491 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 2,414 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 2,144 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.