Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Contributed byMario AlkaGoogle

gemma-3n-E4B-it

Performance benchmark · measured on 22.09.2026 14:15

Benchmark-IDrun-20260922-123035-baae7c
Timebench 3 - Kombi (Prefill + Generation)Dense8BRuntime: llama.cppQuantisierung: Q8_0
Generation277,51tok/s
Prefill4.348,12tok/s
Time to First Token4.623,00ms
Total duration86,89s
Concurrency10parallel
Ranking in the field
This GPUAll GPUs
28of 237 systems

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

This run is better than 89 % of all comparable systems.
Generation 277,5 tok/s
+95 % vs Ø 142,0
Prefill 4.348,1 tok/s
+53 % vs Ø 2.834,3
Time to First Token 4.623 ms
-95 % vs Ø 99.801
Distribution in the field0 – 667 tok/s
Ø 142 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)

AMD Radeon AI PRO R9700 this runrun-20260922-123035-baae7c
277,5 tok/s
2× AMD Radeon RX 7900 XTXrun-20261008-105921-10885d
220,8 tok/s

Hardware

GPU: AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen 3 3100 4-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING

Setup

Runtime: llama.cpp
Quantization: Q8_0
Model: gemma-3n-E4B-it

Configuration

benchmark-konfiguration — run-20260922-123035-baae7c
# LLM-Benchmark Konfiguration # Modell : gemma-3n-E4B-it # Engine : llama.cpp # Run-ID : run-20260922-123035-baae7c # GPU : AMD Radeon AI PRO R9700 # CPU : AMD Ryzen 3 3100 4-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/models/gemma-4-E4B-it-Q8_0.gguf \ --alias gemma-4-E4B-it \ -ngl 999 \ -fa on \ -c 49152 \ -np 12 '(AMD' Radeon AI PRO R9700, ROCm 7.2.4, 'HIP_VISIBLE_DEVICES=0)'
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.49152
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/models/gemma-4-E4B-it-Q8_0.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
faon
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.49152
np12

All benchmarks of this model To leaderboard

Anzeige
Model comparison

gemma-3n-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

3172832492151822.4823.0873.6924.297Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 220,8 tok/s Generation, 2.894 tok/s Prefill, TTFT 3.558 ms (3 Laufe)AMD Radeon RX 7900 XTXAMD Radeon AI PRO R9700 - 277,5 tok/s Generation, 3.885 tok/s Prefill, TTFT 2.589 ms (3 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
★ AMD Radeon AI PRO R9700 277,5 tok/s this runAMD Radeon RX 7900 XTX 220,8 tok/s

CPUby processor

3172832492151822.4823.0873.6924.297Prefill (tok/s)Generation (tok/s)Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 220,8 tok/s Generation, 2.894 tok/s Prefill, TTFT 3.558 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen 3 3100 4-Core Processor - 277,5 tok/s Generation, 3.885 tok/s Prefill, TTFT 2.589 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 3 3100 4-Co...
★ AMD Ryzen 3 3100 4-Core Processor 277,5 tok/s this runIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 220,8 tok/s

MBby mainboard

3172832492151822.4823.0873.6924.297Prefill (tok/s)Generation (tok/s)Dell Inc. PowerEdge R820 - 220,8 tok/s Generation, 2.894 tok/s Prefill, TTFT 3.558 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 277,5 tok/s Generation, 3.885 tok/s Prefill, TTFT 2.589 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 277,5 tok/s this runDell Inc. PowerEdge R820 220,8 tok/s

ENGby engine

3052912782642503.1863.3223.4573.593Prefill (tok/s)Generation (tok/s)llama.cpp - 277,5 tok/s Generation, 3.389 tok/s Prefill, TTFT 3.074 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 277,5 tok/s this run

DRVby driver

3052912782642503.1863.3223.4573.593Prefill (tok/s)Generation (tok/s)unbekannt - 277,5 tok/s Generation, 3.389 tok/s Prefill, TTFT 3.074 ms (6 Laufe)unbekannt
unbekannt 277,5 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 20 W
⚡ TDP 300 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)300 W estimated (TDP)GPU 300 W full load
Avg cost / hourEUR 0.090
Electricity / 1M tokensEUR 0.090
Token / kWh3.33M
Acquisition (system)EUR 1,520 partial priceGPU EUR 1,400 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 3,097
Output tokens (2 years)17.50B
☁️ 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 (20 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-3n-E4B-itAMD Radeon AI PRO R9700gemma-3n-E4B-it2x AMD Radeon RX 7900 XTX
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)––
AMD Radeon AI PRO R9700 · this run 278 tok/s2× AMD Radeon RX 7900 XTX 221 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.