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

gemma-4-12B-it

Performance benchmark · measured on 28.07.2026 19:27

Benchmark-IDrun-20260728-194136-63ca0c
Timebench 3 - Kombi (Prefill + Generation)Dense12BRuntime: llama.cppQuantisierung: UD-Q4_K_XL
Generation360,92tok/s
Prefill2.636,11tok/s
Time to First Token6.319,00ms
Total duration60,24s
Concurrency5parallel
Ranking in the field
10of 40 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 77 % of all comparable systems.
Generation 360,9 tok/s
+57 % vs Ø 230,3
Prefill 2.636,1 tok/s
-21 % vs Ø 3.337,5
Time to First Token 6.319 ms
-86 % vs Ø 44.779
Distribution in the field4 – 974 tok/s
Ø 230 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× 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: UD-Q4_K_XL
Model: gemma-4-12B-it

Configuration

benchmark-konfiguration — run-20260728-194136-63ca0c
# LLM-Benchmark Konfiguration # Modell : gemma-4-12B-it # Engine : llama.cpp # Run-ID : run-20260728-194136-63ca0c # 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-4-12B-it-qat-GGUF/snapshots/980b060c40a8539ac159e0501a3e0f66a6365af3/gemma-4-12B-it-qat-UD-Q4_K_XL.gguf \ --alias gemma-4-12B-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-4-12B-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-4-12B-it-qat-GGUF/snapshots/980b060c40a8539ac159e0501a3e0f66a6365af3/gemma-4-12B-it-qat-UD-Q4_K_XL.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-4-12B-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

1.3001.0958916864822.6993.4954.2925.088Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.104,3 tok/s Generation, 4.570 tok/s Prefill, TTFT 5.144 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5070 Ti - 677,5 tok/s Generation, 3.217 tok/s Prefill, TTFT 5.812 ms (6 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.104,3 tok/s★ NVIDIA GeForce RTX 5070 Ti 677,5 tok/s this run

CPUby processor

1.3001.0958916864822.6993.4954.2925.088Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 1.104,3 tok/s Generation, 4.570 tok/s Prefill, TTFT 5.144 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 677,5 tok/s Generation, 3.217 tok/s Prefill, TTFT 5.812 ms (6 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 1.104,3 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 677,5 tok/s this run

MBby mainboard

1.3001.0958916864822.6993.4954.2925.088Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.104,3 tok/s Generation, 4.570 tok/s Prefill, TTFT 5.144 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 677,5 tok/s Generation, 3.217 tok/s Prefill, TTFT 5.812 ms (6 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.104,3 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 677,5 tok/s this run

ENGby engine

1.3381.0677955242523.4233.5913.7593.928Prefill (tok/s)Generation (tok/s)vLLM - 486,2 tok/s Generation, 3.698 tok/s Prefill, TTFT 3.081 ms (3 Laufe)vLLMllama.cpp - 1.104,3 tok/s Generation, 3.653 tok/s Prefill, TTFT 6.844 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.104,3 tok/s this runvLLM 486,2 tok/s

DRVby driver

1.2151.1601.1041.0499943.4483.5953.7413.888Prefill (tok/s)Generation (tok/s)unbekannt - 1.104,3 tok/s Generation, 3.668 tok/s Prefill, TTFT 5.589 ms (9 Laufe)unbekannt
unbekannt 1.104,3 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (5× 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 0.072
Token / kWh4.19M
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)22.76B
☁️ 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-4-12B-itNVIDIA GeForce RTX 5070 Tigemma-4-12B-itNVIDIA RTX PRO 6000 Blackwell Workstation Editiongemma-4-12B-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.