Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaNVIDIA

Llama-3_1-Nemotron-Ultra-253B-v1

Performance benchmark · measured on 31.07.2026 07:26

Benchmark-IDrun-20260731-083539-315b87
Timebench 3 - Kombi (Prefill + Generation)Dense253BRuntime: llama.cppQuantisierung: Q4_K_M
Generation0,05tok/s
Prefill7,53tok/s
Time to First Token290.462,00ms
Total duration1.200,00s
Concurrency1parallel
Ranking in the field
539of 542 systems

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

This run is better than 1 % of all comparable systems.
Generation 0,1 tok/s
-100 % vs Ø 119,5
Prefill 7,5 tok/s
-100 % vs Ø 3.135,7
Time to First Token 290.462 ms
+1.930 % vs Ø 14.312
Distribution in the field0 – 405 tok/s
Ø 120 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
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-d456e7
393,5 tok/s
NVIDIA-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
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
NVIDIA-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
Llama-3_1-Nemotron-Ultra-253B-v1 this runNVIDIA GeForce RTX 5090 · run-20260731-083539-315b87
0,1 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA GeForce RTX 5090 · 32 GB VRAM
CPU: AMD Ryzen 7 5800X3D 8-Core Processor
RAM: 126 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Llama-3_1-Nemotron-Ultra-253B-v1

Configuration

benchmark-konfiguration — run-20260731-083539-315b87
# LLM-Benchmark Konfiguration # Modell : Llama-3_1-Nemotron-Ultra-253B-v1 # Engine : llama.cpp # Run-ID : run-20260731-083539-315b87 # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--DevQuasar--nvidia.Llama-3_1-Nemotron-Ultra-253B-v1-GGUF/snapshots/fa034db97ae9c144e5d5a8fd8fc4fefdd363b8db/nvidia.Llama-3_1-Nemotron-Ultra-253B-v1.Q4_K_M-00001-of-00012.gguf \ --alias Llama-3_1-Nemotron-Ultra-253B-v1 \ --host 0.0.0.0 \ --port 8000 \ -ngl 0 \ -c 16384 \ -np 4 \ --jinja
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.Llama-3_1-Nemotron-Ultra-253B-v1
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./root/.cache/huggingface/hub/models--DevQuasar--nvidia.Llama-3_1-Nemotron-Ultra-253B-v1-GGUF/snapshots/fa034db97ae9c144e5d5a8fd8fc4fefdd363b8db/nvidia.Llama-3_1-Nemotron-Ultra-253B-v1.Q4_K_M-00001-of-00012.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.0
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Llama-3_1-Nemotron-Ultra-253B-v1 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

2,21,61,10,50,00316192Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 5070 Ti - 1,7 tok/s Generation, 45 tok/s Prefill, TTFT 141.946 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 0,9 tok/s Generation, 24 tok/s Prefill, TTFT 198.709 ms (4 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 0,9 tok/s Generation, 75 tok/s Prefill, TTFT 28.132 ms (1 Lauf)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 0,1 tok/s Generation, 8 tok/s Prefill, TTFT 290.462 ms (1 Lauf) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA GeForce RTX 5070 Ti 1,7 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 0,9 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 0,9 tok/s★ NVIDIA GeForce RTX 5090 0,1 tok/s this run

CPUby processor

2,21,61,10,50,00316192Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 5975WX 32-Cores - 1,7 tok/s Generation, 45 tok/s Prefill, TTFT 141.946 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 0,9 tok/s Generation, 24 tok/s Prefill, TTFT 198.709 ms (4 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 0,9 tok/s Generation, 75 tok/s Prefill, TTFT 28.132 ms (1 Lauf)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 0,1 tok/s Generation, 8 tok/s Prefill, TTFT 290.462 ms (1 Lauf) | DIESER LAUF★ AMD Ryzen 7 5800X3D 8...
AMD Ryzen Threadripper PRO 5975WX 32-Cores 1,7 tok/sAMD Ryzen 9 9950X 16-Core Processor 0,9 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 0,9 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 0,1 tok/s this run

MBby mainboard

2,21,61,10,50,00316192Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 1,7 tok/s Generation, 45 tok/s Prefill, TTFT 141.946 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 0,9 tok/s Generation, 24 tok/s Prefill, TTFT 198.709 ms (4 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 0,9 tok/s Generation, 75 tok/s Prefill, TTFT 28.132 ms (1 Lauf)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 0,1 tok/s Generation, 8 tok/s Prefill, TTFT 290.462 ms (1 Lauf) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1,7 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 0,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 0,9 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 0,1 tok/s this run

ENGby engine

1,81,81,71,61,533343637Prefill (tok/s)Generation (tok/s)llama.cpp - 1,7 tok/s Generation, 35 tok/s Prefill, TTFT 171.030 ms (9 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1,7 tok/s this run

DRVby driver

1,81,81,71,61,533343637Prefill (tok/s)Generation (tok/s)unbekannt - 1,7 tok/s Generation, 35 tok/s Prefill, TTFT 171.030 ms (9 Laufe)unbekannt
unbekannt 1,7 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 URLReset
⚡ Electricity price EUR/kWh
⚙️ System utilization 100 %
🖥️ Acquisition EUR
🔌 Idle 72 W
⚡ TDP 622 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 1,035.83
Token / kWh290
Acquisition (system)EUR 4,986 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 1,008 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 8,253
Output tokens (2 years)3.15M
☁️ 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 (72 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

Llama-3_1-Nemotron-Ultra-253B-v1NVIDIA GeForce RTX 5090Llama-3_1-Nemotron-Ultra-253B-v13x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionLlama-3_1-Nemotron-Ultra-253B-v1NVIDIA GeForce RTX 5070 TiLlama-3_1-Nemotron-Ultra-253B-v1NVIDIA RTX PRO 6000 Blackwell 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)

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.