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

gemma-4-E2B-it

Performance benchmark · measured on 28.07.2026 10:01

Benchmark-IDrun-20260728-140953-875f2e
Timebench 3 - Kombi (Prefill + Generation)Dense5BRuntime: llama.cppQuantisierung: Q4_K_M
Generation1.743,96tok/s
Prefill13.641,45tok/s
Time to First Token5.790,00ms
Total duration39,07s
Concurrency10parallel
Ranking in the field
1of 32 systems

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

This run is better than 100 % of all comparable systems.
Generation 1.744,0 tok/s
+353 % vs Ø 385,3
Prefill 13.641,5 tok/s
+235 % vs Ø 4.070,0
Time to First Token 5.790 ms
-92 % vs Ø 69.846
Distribution in the field3 – 1.744 tok/s
Ø 385 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: gemma-4-E2B-it

Configuration

benchmark-konfiguration — run-20260728-140953-875f2e
# LLM-Benchmark Konfiguration # Modell : gemma-4-E2B-it # Engine : llama.cpp # Run-ID : run-20260728-140953-875f2e # 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--unsloth--gemma-4-E2B-it-GGUF/snapshots/0314792d7f1f7e229411f620751375812bb9faf2/gemma-4-E2B-it-Q4_K_M.gguf \ --alias gemma-4-E2B-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-E2B-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-E2B-it-GGUF/snapshots/0314792d7f1f7e229411f620751375812bb9faf2/gemma-4-E2B-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-E2B-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

3.0852.3141.5437710,06366.93613.23619.537Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 2.414,4 tok/s Generation, 16.315 tok/s Prefill, TTFT 1.871 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 1.492,8 tok/s Generation, 9.978 tok/s Prefill, TTFT 3.182 ms (3 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 266,1 tok/s Generation, 3.857 tok/s Prefill, TTFT 15.559 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5070 Ti - 1.744,0 tok/s Generation, 15.451 tok/s Prefill, TTFT 2.253 ms (8 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 2.414,4 tok/s★ NVIDIA GeForce RTX 5070 Ti 1.744,0 tok/s this runNVIDIA GeForce RTX 3090 Ti 1.492,8 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 266,1 tok/s

CPUby processor

3.0852.3141.5437710,06366.93613.23619.537Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 2.414,4 tok/s Generation, 16.315 tok/s Prefill, TTFT 1.871 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 9 8945HX with Radeon Graphics - 1.492,8 tok/s Generation, 9.978 tok/s Prefill, TTFT 3.182 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 266,1 tok/s Generation, 3.857 tok/s Prefill, TTFT 15.559 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 1.744,0 tok/s Generation, 15.451 tok/s Prefill, TTFT 2.253 ms (8 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 2.414,4 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 1.744,0 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 1.492,8 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 266,1 tok/s

MBby mainboard

3.0852.3141.5437710,06366.93613.23619.537Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 2.414,4 tok/s Generation, 16.315 tok/s Prefill, TTFT 1.871 ms (3 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 1.492,8 tok/s Generation, 9.978 tok/s Prefill, TTFT 3.182 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 266,1 tok/s Generation, 3.857 tok/s Prefill, TTFT 15.559 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 1.744,0 tok/s Generation, 15.451 tok/s Prefill, TTFT 2.253 ms (8 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 2.414,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 1.744,0 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 1.492,8 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 266,1 tok/s

ENGby engine

2.8172.4142.0111.6091.2067.17913.26219.34625.430Prefill (tok/s)Generation (tok/s)vLLM - 1.608,5 tok/s Generation, 22.042 tok/s Prefill, TTFT 757 ms (3 Laufe)vLLMllama.cpp - 2.414,4 tok/s Generation, 10.567 tok/s Prefill, TTFT 5.542 ms (14 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 2.414,4 tok/s this runvLLM 1.608,5 tok/s

DRVby driver

2.6562.5352.4142.2942.17311.83612.34012.84413.347Prefill (tok/s)Generation (tok/s)unbekannt - 2.414,4 tok/s Generation, 12.592 tok/s Prefill, TTFT 4.698 ms (17 Laufe)unbekannt
unbekannt 2.414,4 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 0.015
Token / kWh20.25M
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)110.00B
☁️ 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

gemma-4-E2B-itNVIDIA GeForce RTX 5070 Tigemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Editiongemma-4-E2B-itNVIDIA GeForce RTX 5070 Tigemma-4-E2B-itNVIDIA 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.