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

Llama-3.3-Nemotron-Super-49B-v1.5

Performance benchmark · measured on 29.07.2026 07:57

Benchmark-IDrun-20260729-105334-640dbf
Timebench 3 - Kombi (Prefill + Generation)Dense49BRuntime: llama.cppQuantisierung: Q4_K_M
Generation25,18tok/s
Prefill260,73tok/s
Time to First Token255.649,50ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
1073of 1205 systems

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

This run is better than 11 % of all comparable systems.
Generation 25,2 tok/s
-94 % vs Ø 452,5
Prefill 260,7 tok/s
-96 % vs Ø 6.563,7
Time to First Token 255.650 ms
+446 % vs Ø 46.854
Distribution in the field0 – 2.491 tok/s
Ø 452 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e28775
2.491,2 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-b37ed9
2.414,4 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9c966e
1.995,4 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-e0eafd
1.897,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-7c961d
1.890,7 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd
1.878,7 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b
1.835,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046
1.830,3 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-c6e7e0
1.819,5 tok/s
Llama-3.3-Nemotron-Super-49B-v1.5 this runNVIDIA GeForce RTX 5070 Ti · run-20260729-105334-640dbf
25,2 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA GeForce RTX 5070 Ti · 16 GB VRAM
CPU: AMD Ryzen Threadripper PRO 5975WX 32-Cores
RAM: 247 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Llama-3.3-Nemotron-Super-49B-v1.5

Configuration

benchmark-konfiguration — run-20260729-105334-640dbf
# LLM-Benchmark Konfiguration # Modell : Llama-3.3-Nemotron-Super-49B-v1.5 # Engine : llama.cpp # Run-ID : run-20260729-105334-640dbf # GPU : NVIDIA GeForce RTX 5070 Ti # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--gabriellarson--Llama-3_3-Nemotron-Super-49B-v1_5-GGUF/snapshots/c324e134daf0a0d4f9e3e136ae525df9fdebea3b/Llama-3_3-Nemotron-Super-49B-v1_5-Q4_K_M.gguf \ --alias Llama-3_3-Nemotron-Super-49B-v1_5 \ --host 0.0.0.0 \ --port 8000 \ -ngl 30 \ -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_3-Nemotron-Super-49B-v1_5
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./home/godcore/.cache/huggingface/hub/models--gabriellarson--Llama-3_3-Nemotron-Super-49B-v1_5-GGUF/snapshots/c324e134daf0a0d4f9e3e136ae525df9fdebea3b/Llama-3_3-Nemotron-Super-49B-v1_5-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.30
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-3.3-Nemotron-Super-49B-v1.5 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

4713532351180,001.0242.0473.071Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 364,1 tok/s Generation, 2.480 tok/s Prefill, TTFT 13.861 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 303,0 tok/s Generation, 2.253 tok/s Prefill, TTFT 17.522 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX A6000 - 197,3 tok/s Generation, 2.201 tok/s Prefill, TTFT 19.347 ms (12 Laufe)NVIDIA RTX A6000AMD Radeon PRO W7900 Dual Slot - 71,0 tok/s Generation, 517 tok/s Prefill, TTFT 24.661 ms (3 Laufe)AMD Radeon PRO W7900 ...NVIDIA GeForce RTX 5090 - 20,2 tok/s Generation, 333 tok/s Prefill, TTFT 137.310 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 3090 Ti - 19,6 tok/s Generation, 407 tok/s Prefill, TTFT 91.059 ms (3 Laufe)NVIDIA GeForce RTX 30...AMD Radeon AI PRO R9700 - 11,6 tok/s Generation, 23 tok/s Prefill, TTFT 293.489 ms (9 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 25,2 tok/s Generation, 243 tok/s Prefill, TTFT 129.179 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 364,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 303,0 tok/sNVIDIA RTX A6000 197,3 tok/sAMD Radeon PRO W7900 Dual Slot 71,0 tok/s★ NVIDIA GeForce RTX 5070 Ti 25,2 tok/s this runNVIDIA GeForce RTX 5090 20,2 tok/sNVIDIA GeForce RTX 3090 Ti 19,6 tok/sAMD Radeon AI PRO R9700 11,6 tok/s

CPUby processor

4693522351170,001.0052.0103.015Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 364,1 tok/s Generation, 2.480 tok/s Prefill, TTFT 13.861 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 303,0 tok/s Generation, 2.253 tok/s Prefill, TTFT 17.522 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 197,3 tok/s Generation, 1.267 tok/s Prefill, TTFT 136.837 ms (21 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 20,2 tok/s Generation, 333 tok/s Prefill, TTFT 137.310 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen 9 8945HX with Radeon Graphics - 19,6 tok/s Generation, 407 tok/s Prefill, TTFT 91.059 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 71,0 tok/s Generation, 380 tok/s Prefill, TTFT 76.920 ms (6 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 364,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 303,0 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 197,3 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 71,0 tok/s this runAMD Ryzen 7 5800X3D 8-Core Processor 20,2 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,6 tok/s

MBby mainboard

4693522351170,001.0052.0103.015Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 364,1 tok/s Generation, 2.480 tok/s Prefill, TTFT 13.861 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 303,0 tok/s Generation, 1.563 tok/s Prefill, TTFT 101.042 ms (30 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 20,2 tok/s Generation, 333 tok/s Prefill, TTFT 137.310 ms (3 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 19,6 tok/s Generation, 407 tok/s Prefill, TTFT 91.059 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 71,0 tok/s Generation, 380 tok/s Prefill, TTFT 76.920 ms (6 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 364,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 303,0 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 71,0 tok/s this runASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 20,2 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 19,6 tok/s

ENGby engine

4343572812041273291.5832.8384.092Prefill (tok/s)Generation (tok/s)vLLM - 197,3 tok/s Generation, 3.442 tok/s Prefill, TTFT 4.578 ms (6 Laufe)vLLMllama.cpp - 364,1 tok/s Generation, 979 tok/s Prefill, TTFT 107.487 ms (39 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 364,1 tok/s this runvLLM 197,3 tok/s

DRVby driver

4003823643463281.2291.2811.3341.386Prefill (tok/s)Generation (tok/s)unbekannt - 364,1 tok/s Generation, 1.307 tok/s Prefill, TTFT 93.766 ms (45 Laufe)unbekannt
unbekannt 364,1 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (10× 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 10 W
⚡ TDP 310 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)310 W estimated (TDP)GPU 300 + Board 10 W full load
Avg cost / hourEUR 0.093
Electricity / 1M tokensEUR 1.03
Token / kWh292.41K
Acquisition (system)EUR 5,000 partial priceGPU EUR 994 · CPU EUR 1,880 · RAM EUR 1,976 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 6,629
Output tokens (2 years)1.59B
☁️ 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 (10 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-3.3-Nemotron-Super-49B-v1.5NVIDIA GeForce RTX 5070 TiLlama-3.3-Nemotron-Super-49B-v1.5NVIDIA RTX PRO 6000 Blackwell Workstation EditionLlama-3.3-Nemotron-Super-49B-v1.53x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionLlama-3.3-Nemotron-Super-49B-v1.53x 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)

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.