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

Generation45,80tok/s

Prefill1.823,08tok/s

Time to First Token1.259,00ms

Total duration47,24s

Concurrency1parallel

Ranking in the field

This GPU All GPUs

952of 1808 systems

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

This run is better than 47 % of all comparable systems.

Generation 45,8 tok/s

-41 % vs Ø 77,1

Prefill 1.823,1 tok/s

-36 % vs Ø 2.836,4

Time to First Token 1.259 ms

-95 % vs Ø 25.162

Distribution in the field0 – 405 tok/s

Ø 77 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004608-16af9b

404,6 tok/s

gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9f766a

395,2 tok/s

Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7

393,5 tok/s

Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bffb11

393,5 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260724-004607-29bd16

388,9 tok/s

gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-1c779f

388,2 tok/s

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-6ea089

378,6 tok/s

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e8b129

377,6 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e

362,3 tok/s

Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085

361,4 tok/s

Nemotron-3-Nano-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105335-653788

359,4 tok/s

Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA GeForce RTX 5090 · run-20260729-105334-2c4905

359,3 tok/s

Nemotron-Cascade-2-30B-A3BNVIDIA GeForce RTX 5090 · run-20260729-105334-44d1e7

359,0 tok/s

Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-4852bf

357,1 tok/s

Mistral-Small-3.1-24B-Instruct-2503 this run2× 2x AMD Radeon RX 7900 XTX · run-20261009-081229-2c3d29

45,8 tok/s

How does this benchmark compare on other GPUs?

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

AMD Radeon PRO W7900 Dual Slotrun-20260818-003841-e4b3b8

49,1 tok/s

AMD Radeon RX 7900 XTXrun-20260922-123036-d323a5

46,7 tok/s

2× AMD Radeon RX 7900 XTX this runrun-20261009-081229-2c3d29

45,8 tok/s

2× NVIDIA RTX A6000run-20260830-011927-6159d8

44,4 tok/s

2× NVIDIA RTX A6000run-20260827-185904-407b57

44,4 tok/s

2× AMD Radeon PRO W7900 Dual Slotrun-20260818-115056-d40760

39,0 tok/s

NVIDIA RTX A6000run-20260826-065247-76b2d6

38,4 tok/s

AMD Radeon AI PRO R9700run-20260922-063731-a56df0

33,5 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165909-428031

33,1 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165907-01396d

33,1 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165906-4b8178

33,0 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165905-e839b4

33,0 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165909-c33041

31,3 tok/s

3× AMD Radeon AI PRO R9700run-20260722-165907-63e728

31,3 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: Mistral-Small-3.1-24B-Instruct-2503

Configuration

benchmark-konfiguration — run-20261009-081229-2c3d29

# LLM-Benchmark Konfiguration # Modell : Mistral-Small-3.1-24B-Instruct-2503 # Engine : llama.cpp # Run-ID : run-20261009-081229-2c3d29 # 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 mistralai_Mistral-Small-3.1-24B-Instruct-2503-IQ4_XS.gguf \ --alias Mistral-Small-3.1-24B-Instruct-2503 \ -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.	Mistral-Small-3.1-24B-Instruct-2503
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.	mistralai_Mistral-Small-3.1-24B-Instruct-2503-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

Mistral-Small-3.1-24B-Instruct-2503 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 A6000 214,9 tok/s★ AMD Radeon RX 7900 XTX 170,1 tok/s this runAMD Radeon PRO W7900 Dual Slot 150,4 tok/sAMD Radeon PRO W7800 48GB 141,9 tok/sAMD Radeon AI PRO R9700 133,1 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 88,3 tok/sAMD Radeon 8060S Graphics 31,3 tok/sNVIDIA Tesla P100 PCIe 16GB 23,8 tok/s

CPUby processor

AMD Ryzen Threadripper PRO 7955WX 16-Cores 214,9 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 170,1 tok/s this runAMD Ryzen Threadripper PRO 3955WX 16-Cores 151,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 150,4 tok/sAMD Ryzen 3 3100 4-Core Processor 133,1 tok/sAMD Ryzen 9 9950X 16-Core Processor 88,3 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 31,3 tok/sAMD Ryzen 9 7945HX with Radeon Graphics 23,8 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 214,9 tok/s★ Dell Inc. PowerEdge R820 170,1 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 151,5 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 133,1 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 88,3 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd SHWSA (MS-S1 MAX) 31,3 tok/sShenzhen Meigao Electronic Equipment Co.,Ltd F1FXM (DeskMini Series) 23,8 tok/s

ENGby engine

★ llama.cpp 214,9 tok/s this runvLLM 99,3 tok/sunbekannt 33,1 tok/s

DRVby driver

unbekannt 214,9 tok/sAMD 7.0.0-27-generic 33,1 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 1.36

Token / kWh220.21K

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)2.89B

☁️ 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

	Mistral-Small-3.1-24B-Instruct-25032x AMD Radeon RX 7900 XTX	Mistral-Small-3.1-24B-Instruct-2503AMD Radeon PRO W7900 Dual Slot	Mistral-Small-3.1-24B-Instruct-2503AMD Radeon RX 7900 XTX	Mistral-Small-3.1-24B-Instruct-25032x 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 46 tok/s AMD Radeon PRO W7900 Dual Slot 49 tok/s AMD Radeon RX 7900 XTX 47 tok/s 2× NVIDIA RTX A6000 44 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.