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 11:39

Benchmark-IDrun-20260729-122848-a31762
Timebench 3 - Kombi (Prefill + Generation)Dense49BRuntime: llama.cppQuantisierung: Q4_K_M
Generation19,60tok/s
Prefill426,67tok/s
Time to First Token182.825,00ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
385of 425 systems

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

This run is better than 9 % of all comparable systems.
Generation 19,6 tok/s
-97 % vs Ø 709,7
Prefill 426,7 tok/s
-94 % vs Ø 6.837,0
Time to First Token 182.825 ms
+352 % vs Ø 40.485
Distribution in the field0 – 2.491 tok/s
Ø 710 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
NVIDIA-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-20260728-140954-8007c4
1.993,5 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
NVIDIA-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
NVIDIA-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
NVIDIA-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
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-2b99aa
1.802,0 tok/s
Llama-3_3-Nemotron-Super-49B-v1_5 this runNVIDIA GeForce RTX 3090 Ti · run-20260729-122848-a31762
19,6 tok/s

How does this benchmark compare on other GPUs?

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

Configuration

benchmark-konfiguration — run-20260729-122848-a31762
# LLM-Benchmark Konfiguration # Modell : Llama-3_3-Nemotron-Super-49B-v1_5 # Engine : llama.cpp # Run-ID : run-20260729-122848-a31762 # GPU : NVIDIA GeForce RTX 3090 Ti # CPU : AMD Ryzen 9 8945HX with Radeon Graphics # RAM : 92 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.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 60 \ -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./root/.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.60
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

4703532351180,001.0102.0213.031Prefill (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...AMD Radeon AI PRO R9700 - 42,1 tok/s Generation, 2.262 tok/s Prefill, TTFT 9.025 ms (2 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)NVIDIA GeForce RTX 50...AMD Radeon 8060S Graphics - 14,3 tok/s Generation, 306 tok/s Prefill, TTFT 40.454 ms (3 Laufe)AMD Radeon 8060S Grap...NVIDIA GeForce RTX 3090 Ti - 19,6 tok/s Generation, 407 tok/s Prefill, TTFT 91.059 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 30...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 364,1 tok/sAMD Radeon AI PRO R9700 42,1 tok/sNVIDIA GeForce RTX 5070 Ti 25,2 tok/s★ NVIDIA GeForce RTX 3090 Ti 19,6 tok/s this runAMD Radeon 8060S Graphics 14,3 tok/s

CPUby processor

4703532351180,001.0102.0213.031Prefill (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 7955WX 16-Cores - 42,1 tok/s Generation, 2.262 tok/s Prefill, TTFT 9.025 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 25,2 tok/s Generation, 243 tok/s Prefill, TTFT 129.179 ms (3 Laufe)AMD Ryzen Threadrippe...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 14,3 tok/s Generation, 306 tok/s Prefill, TTFT 40.454 ms (3 Laufe)AMD RYZEN AI MAX+ 395...AMD Ryzen 9 8945HX with Radeon Graphics - 19,6 tok/s Generation, 407 tok/s Prefill, TTFT 91.059 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 8945HX wi...
AMD Ryzen 9 9950X 16-Core Processor 364,1 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 42,1 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 25,2 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 19,6 tok/s this runAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 14,3 tok/s

MBby mainboard

4703532351180,001.0102.0213.031Prefill (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 - 42,1 tok/s Generation, 2.262 tok/s Prefill, TTFT 9.025 ms (2 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 25,2 tok/s Generation, 243 tok/s Prefill, TTFT 129.179 ms (3 Laufe)ASUSTeK COMPUTER INC....Bosgame AXB35-02 (BeyondMax Series) - 14,3 tok/s Generation, 306 tok/s Prefill, TTFT 40.454 ms (3 Laufe)Bosgame AXB35-02 (Bey...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) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 364,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 42,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 25,2 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 19,6 tok/s this runBosgame AXB35-02 (BeyondMax Series) 14,3 tok/s

ENGby engine

4003823643463289961.0381.0801.123Prefill (tok/s)Generation (tok/s)llama.cpp - 364,1 tok/s Generation, 1.059 tok/s Prefill, TTFT 60.122 ms (14 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 364,1 tok/s this run

DRVby driver

4003823643463289961.0381.0801.123Prefill (tok/s)Generation (tok/s)unbekannt - 364,1 tok/s Generation, 1.059 tok/s Prefill, TTFT 60.122 ms (14 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 50 W
⚡ TDP 477 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)477 W estimated (TDP)GPU 450 + CPU 17 + Board 10 W full load
Avg cost / hourEUR 0.14
Electricity / 1M tokensEUR 2.03
Token / kWh147.85K
Acquisition (system)EUR 2,986 partial priceGPU EUR 999 · CPU EUR 549 · RAM EUR 1,288 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 5,494
Output tokens (2 years)1.24B
☁️ 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 (50 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 3090 TiLlama-3_3-Nemotron-Super-49B-v1_5NVIDIA RTX PRO 6000 Blackwell Workstation EditionLlama-3_3-Nemotron-Super-49B-v1_53x AMD Radeon AI PRO R9700Llama-3_3-Nemotron-Super-49B-v1_5NVIDIA GeForce RTX 5070 Ti
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.