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

Nemotron-H-47B-Reasoning-128K

Performance benchmark · measured on 29.07.2026 07:03

Benchmark-IDrun-20260729-105332-338119
Timebench 3 - Kombi (Prefill + Generation)Dense47BRuntime: llama.cppQuantisierung: Q4_K_M
Generation20,39tok/s
Prefill172,19tok/s
Time to First Token265.240,50ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
55of 66 systems

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

This run is better than 17 % of all comparable systems.
Generation 20,4 tok/s
-93 % vs Ø 294,6
Prefill 172,2 tok/s
-94 % vs Ø 2.747,8
Time to First Token 265.241 ms
+184 % vs Ø 93.382
Distribution in the field3 – 1.744 tok/s
Ø 295 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

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: Nemotron-H-47B-Reasoning-128K

Configuration

benchmark-konfiguration — run-20260729-105332-338119
# LLM-Benchmark Konfiguration # Modell : Nemotron-H-47B-Reasoning-128K # Engine : llama.cpp # Run-ID : run-20260729-105332-338119 # 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--bartowski--nvidia_Nemotron-H-47B-Reasoning-128K-GGUF/snapshots/ce89f02cd0eafe3931acec38f4d91a654ae1ca4d/nvidia_Nemotron-H-47B-Reasoning-128K-Q4_K_M.gguf \ --alias Nemotron-H-47B-Reasoning-128K \ --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.Nemotron-H-47B-Reasoning-128K
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--bartowski--nvidia_Nemotron-H-47B-Reasoning-128K-GGUF/snapshots/ce89f02cd0eafe3931acec38f4d91a654ae1ca4d/nvidia_Nemotron-H-47B-Reasoning-128K-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

Nemotron-H-47B-Reasoning-128K 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

22416811256,00,003777551.132Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 174,9 tok/s Generation, 938 tok/s Prefill, TTFT 18.279 ms (3 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon AI PRO R9700 - 24,9 tok/s Generation, 462 tok/s Prefill, TTFT 21.185 ms (1 Lauf)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 3090 Ti - 16,9 tok/s Generation, 215 tok/s Prefill, TTFT 138.108 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 20,4 tok/s Generation, 168 tok/s Prefill, TTFT 134.329 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 174,9 tok/sAMD Radeon AI PRO R9700 24,9 tok/s★ NVIDIA GeForce RTX 5070 Ti 20,4 tok/s this runNVIDIA GeForce RTX 3090 Ti 16,9 tok/s

CPUby processor

22416811256,00,003777551.132Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 174,9 tok/s Generation, 938 tok/s Prefill, TTFT 18.279 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 24,9 tok/s Generation, 462 tok/s Prefill, TTFT 21.185 ms (1 Lauf)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 16,9 tok/s Generation, 215 tok/s Prefill, TTFT 138.108 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 20,4 tok/s Generation, 168 tok/s Prefill, TTFT 134.329 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 174,9 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 24,9 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 20,4 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 16,9 tok/s

MBby mainboard

22416811256,00,003777551.132Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 174,9 tok/s Generation, 938 tok/s Prefill, TTFT 18.279 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 24,9 tok/s Generation, 462 tok/s Prefill, TTFT 21.185 ms (1 Lauf)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 16,9 tok/s Generation, 215 tok/s Prefill, TTFT 138.108 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 20,4 tok/s Generation, 168 tok/s Prefill, TTFT 134.329 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 174,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 24,9 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 20,4 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 16,9 tok/s

ENGby engine

192184175166157416433451469Prefill (tok/s)Generation (tok/s)llama.cpp - 174,9 tok/s Generation, 442 tok/s Prefill, TTFT 89.333 ms (10 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 174,9 tok/s this run

DRVby driver

192184175166157416433451469Prefill (tok/s)Generation (tok/s)unbekannt - 174,9 tok/s Generation, 442 tok/s Prefill, TTFT 89.333 ms (10 Laufe)unbekannt
unbekannt 174,9 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 1.27
Token / kWh236.79K
Acquisition (system)EUR 2,126 missingRAM EUR 1,976 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 3,755
Output tokens (2 years)1.29B
☁️ 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

Nemotron-H-47B-Reasoning-128KNVIDIA GeForce RTX 5070 TiNemotron-H-47B-Reasoning-128KNVIDIA RTX PRO 6000 Blackwell Workstation EditionNemotron-H-47B-Reasoning-128KNVIDIA GeForce RTX 3090 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.