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

gemma-4-E4B-it

Performance benchmark · measured on 28.07.2026 18:55

Benchmark-IDrun-20260728-194135-4155e1
Timebench 3 - Kombi (Prefill + Generation)Dense8BRuntime: llama.cppQuantisierung: Q4_K_M
Generation1.421,79tok/s
Prefill12.417,96tok/s
Time to First Token6.979,50ms
Total duration46,10s
Concurrency10parallel
Ranking in the field
12of 41 systems

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

This run is better than 73 % of all comparable systems.
Generation 1.421,8 tok/s
+76 % vs Ø 807,0
Prefill 12.418,0 tok/s
+65 % vs Ø 7.506,9
Time to First Token 6.980 ms
-59 % vs Ø 17.148
Distribution in the field55 – 2.144 tok/s
Ø 807 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 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-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
Laguna-XS-2.13× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-140954-cb60a0
1.615,3 tok/s
Laguna-XS-2.13× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-140954-12a4c5
1.611,0 tok/s
Laguna-XS-2.13× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-140954-593df2
1.606,1 tok/s
North-Mini-Code-1.03× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-164528-6eb96d
1.490,7 tok/s
gemma-4-E4B-it same model3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194135-d086e1
1.423,3 tok/s
gemma-4-E4B-it this run3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194135-4155e1
1.421,8 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260724-082940-10761f
1.238,3 tok/s
gpt-oss-120b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034051-d52467
1.229,7 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: gemma-4-E4B-it

Configuration

benchmark-konfiguration — run-20260728-194135-4155e1
# LLM-Benchmark Konfiguration # Modell : gemma-4-E4B-it # Engine : llama.cpp # Run-ID : run-20260728-194135-4155e1 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 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
np4

All benchmarks of this model To leaderboard

Anzeige
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

2.0891.7301.3711.0126533.7217.13910.55713.975Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.758,6 tok/s Generation, 12.085 tok/s Prefill, TTFT 2.684 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 1.606,1 tok/s Generation, 8.848 tok/s Prefill, TTFT 2.968 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 5070 Ti - 1.082,4 tok/s Generation, 9.183 tok/s Prefill, TTFT 2.840 ms (6 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 3090 Ti - 983,7 tok/s Generation, 6.659 tok/s Prefill, TTFT 4.857 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.423,3 tok/s Generation, 5.611 tok/s Prefill, TTFT 17.220 ms (12 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.758,6 tok/sNVIDIA GeForce RTX 5090 1.606,1 tok/s★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.423,3 tok/s this runNVIDIA GeForce RTX 5070 Ti 1.082,4 tok/sNVIDIA GeForce RTX 3090 Ti 983,7 tok/s

CPUby processor

2.0891.7301.3711.0126533.7217.13910.55713.975Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 1.758,6 tok/s Generation, 12.085 tok/s Prefill, TTFT 2.684 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 1.606,1 tok/s Generation, 8.848 tok/s Prefill, TTFT 2.968 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 1.082,4 tok/s Generation, 9.183 tok/s Prefill, TTFT 2.840 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 983,7 tok/s Generation, 6.659 tok/s Prefill, TTFT 4.857 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.423,3 tok/s Generation, 5.611 tok/s Prefill, TTFT 17.220 ms (12 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 1.758,6 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.606,1 tok/s★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 1.423,3 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 1.082,4 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 983,7 tok/s

MBby mainboard

2.0891.7301.3711.0126533.7217.13910.55713.975Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.758,6 tok/s Generation, 12.085 tok/s Prefill, TTFT 2.684 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.606,1 tok/s Generation, 8.848 tok/s Prefill, TTFT 2.968 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 1.082,4 tok/s Generation, 9.183 tok/s Prefill, TTFT 2.840 ms (6 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 983,7 tok/s Generation, 6.659 tok/s Prefill, TTFT 4.857 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.423,3 tok/s Generation, 5.611 tok/s Prefill, TTFT 17.220 ms (12 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.758,6 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.606,1 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.423,3 tok/s this runASUSTeK 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

ENGby engine

2.0821.7361.3911.0457004.9758.35811.74215.126Prefill (tok/s)Generation (tok/s)vLLM - 1.022,8 tok/s Generation, 13.200 tok/s Prefill, TTFT 1.096 ms (3 Laufe)vLLMllama.cpp - 1.758,6 tok/s Generation, 6.901 tok/s Prefill, TTFT 10.497 ms (24 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.758,6 tok/s this runvLLM 1.022,8 tok/s

DRVby driver

1.9341.8461.7591.6711.5837.1447.4497.7538.057Prefill (tok/s)Generation (tok/s)unbekannt - 1.758,6 tok/s Generation, 7.601 tok/s Prefill, TTFT 9.452 ms (27 Laufe)unbekannt
unbekannt 1.758,6 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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.058
Token / kWh5.21M
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)89.68B
☁️ 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 (165 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-it3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editiongemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Editiongemma-4-E4B-itNVIDIA GeForce RTX 5090gemma-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)

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.