ℹ

For context: Diese Plattform nutzt Unified Memory – die "VRAM" ist gemeinsamer System-RAM (APU/Superchip); das Modell teilt sich den Speicher mit dem System.

Generation63,50tok/s

Prefill2.576,00tok/s

Time to First Token768,50ms

Total duration33,79s

Concurrency1parallel

Ranking in the field

This GPU All GPUs

280of 481 systems

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

This run is better than 42 % of all comparable systems.

Generation 63,5 tok/s

-48 % vs Ø 123,2

Prefill 2.576,0 tok/s

-21 % vs Ø 3.261,2

Time to First Token 769 ms

-94 % vs Ø 11.966

Distribution in the field0 – 405 tok/s

Ø 123 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

gemma-4-E4B-it this runNVIDIA GB10 · run-20260730-084905-ef5ef1

63,5 tok/s

How does this benchmark compare on other GPUs?

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

NVIDIA GeForce RTX 5090run-20260728-194134-a5655a

247,9 tok/s

NVIDIA RTX PRO 6000 Blackwell Workstation Editionrun-20260727-181607-d807ba

246,5 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-194135-1426a1

223,4 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-194135-5aa8e7

209,0 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-090152-82df54

165,0 tok/s

NVIDIA GeForce RTX 3090 Tirun-20260727-142111-abcb0a

155,8 tok/s

NVIDIA GeForce RTX 5070 Tirun-20260727-032758-68f60a

144,6 tok/s

Intel Arc Pro B70run-20260729-224611-4e9392

84,7 tok/s

NVIDIA GB10 this runrun-20260730-084905-ef5ef1

63,5 tok/s

NVIDIA GB10run-20260729-224611-11c64f

60,5 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260728-194135-4b5d46

25,7 tok/s

3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editionrun-20260727-181605-2d76c2

25,6 tok/s

Hardware

GPU: NVIDIA GB10 · 128 GB VRAM
CPU: NVIDIA Grace
RAM: 120 GB
Mainboard: ASUSTeK COMPUTER INC. GX10

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Driver: NVIDIA 590.48.01 / CUDA 13.1
Model: gemma-4-E4B-it

Configuration

benchmark-konfiguration — run-20260730-084905-ef5ef1

# LLM-Benchmark Konfiguration # Modell : gemma-4-E4B-it # Engine : llama.cpp # Run-ID : run-20260730-084905-ef5ef1 # GPU : NVIDIA GB10 # CPU : NVIDIA Grace # RAM : 120 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--unsloth--gemma-4-E4B-it-GGUF/snapshots/bfc15c382204943c3a8fff0c750b94ae2364d7a3/gemma-4-E4B-it-Q4_K_M.gguf \ --alias gemma-4-E4B-it \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -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.	gemma-4-E4B-it
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--unsloth--gemma-4-E4B-it-GGUF/snapshots/bfc15c382204943c3a8fff0c750b94ae2364d7a3/gemma-4-E4B-it-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.	999
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.	16384
np	4

All benchmarks of this model To leaderboard

Model comparison

gemma-4-E4B-it 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 PRO 6000 Blackwell Workstation Edition 1.758,6 tok/sNVIDIA GeForce RTX 5090 1.606,1 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.423,3 tok/sNVIDIA GeForce RTX 5070 Ti 1.082,4 tok/sNVIDIA GeForce RTX 3090 Ti 983,7 tok/s★ NVIDIA GB10 (DGX Spark) 488,2 tok/s this runIntel Arc Pro B70 474,8 tok/s

CPUby processor

AMD Ryzen 9 9950X 16-Core Processor 1.758,6 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.606,1 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.423,3 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 1.082,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 983,7 tok/s★ NVIDIA Grace 488,2 tok/s this runAMD Ryzen 9 7945HX with Radeon Graphics 474,8 tok/s

MBby mainboard

ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.758,6 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.606,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.423,3 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1.082,4 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 983,7 tok/s★ ASUSTeK COMPUTER INC. GX10 488,2 tok/s this runShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 474,8 tok/s

ENGby engine

★ llama.cpp 1.758,6 tok/s this runvLLM 1.022,8 tok/s

DRVby driver

unbekannt 1.758,6 tok/s★ NVIDIA 590.48.01 / CUDA 13.1 488,2 tok/s this run

💰 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 15 W

⚡ TDP 140 W

☁️ External LLM (API) show

Input €/1M Output €/1M Input per output token

Electricity0.30 EUR/kWh

Avg power (incl. idle)140 W estimated (TDP)GPU 140 W full load

Avg cost / hourEUR 0.042

Electricity / 1M tokensEUR 0.18

Token / kWh1.63M

Acquisition (system)EUR 5,800 partial priceGPU EUR 4,000 · RAM EUR 1,680 · PSU EUR 120

Electricity (2 years)–

TCO (2 years)EUR 6,536

Output tokens (2 years)4.01B

☁️ 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 (15 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

	gemma-4-E4B-itNVIDIA GB10 (DGX Spark)	gemma-4-E4B-itNVIDIA GeForce RTX 5090	gemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition	gemma-4-E4B-it3x 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)	–	–	–	–

NVIDIA GB10 (DGX Spark) · this run 64 tok/s NVIDIA GeForce RTX 5090 248 tok/s NVIDIA RTX PRO 6000 Blackwell Workstation Edition 247 tok/s 3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 223 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.