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

gemma-4-31B-it

Performance benchmark · measured on 27.08.2026 18:38

Benchmark-IDrun-20260827-164707-e83607
Timebench 3 - Kombi (Prefill + Generation)Dense31BRuntime: vLLMQuantisierung: AWQ
Generation222,83tok/s
Prefill5.036,80tok/s
Time to First Token6.267,00ms
Total duration105,10s
Concurrency10parallel
Ranking in the field
127of 168 systems

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

This run is better than 25 % of all comparable systems.
Generation 222,8 tok/s
-40 % vs Ø 369,2
Prefill 5.036,8 tok/s
-57 % vs Ø 11.842,8
Time to First Token 6.267 ms
-6 % vs Ø 6.702
Distribution in the field32 – 1.359 tok/s
Ø 369 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: 2x NVIDIA RTX A6000 · 48 GB VRAM
CPU: AMD Ryzen Threadripper PRO 7955WX 16-Cores
RAM: 184 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: vLLM
Quantization: AWQ
Model: gemma-4-31B-it

Configuration

benchmark-konfiguration — run-20260827-164707-e83607
# LLM-Benchmark Konfiguration # Modell : gemma-4-31B-it # Engine : vLLM # Run-ID : run-20260827-164707-e83607 # GPU : 2x NVIDIA RTX A6000 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ vllm \ --tensor-parallel-size 2 \ --max-model-len 16384 '(2x' RTX A6000 '48GB)'
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.vllm
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.16384
Tensor-Parallel?Anzahl GPUs, auf die JEDER einzelne Modell-Layer aufgeteilt wird (Tensor-Parallelitaet). Mehr GPUs = mehr VRAM und meist mehr Speed, aber die Anzahl der Attention-Heads muss durch diesen Wert teilbar sein (z.B. 32 Heads -> nur 1, 2, 4, 8 ... moeglich, NICHT 3).2
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384

All benchmarks of this model To leaderboard

Anzeige
Model comparison

gemma-4-31B-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

30222715175,60,001.1242.2483.372Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 3090 Ti - 174,1 tok/s Generation, 821 tok/s Prefill, TTFT 31.157 ms (7 Laufe)NVIDIA GeForce RTX 30...AMD Radeon PRO W7900 Dual Slot - 101,9 tok/s Generation, 351 tok/s Prefill, TTFT 52.767 ms (6 Laufe)AMD Radeon PRO W7900 ...AMD Radeon AI PRO R9700 - 24,4 tok/s Generation, 219 tok/s Prefill, TTFT 271 ms (8 Laufe)AMD Radeon AI PRO R97...NVIDIA RTX A6000 - 236,4 tok/s Generation, 2.752 tok/s Prefill, TTFT 10.908 ms (15 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
★ NVIDIA RTX A6000 236,4 tok/s this runNVIDIA GeForce RTX 3090 Ti 174,1 tok/sAMD Radeon PRO W7900 Dual Slot 101,9 tok/sAMD Radeon AI PRO R9700 24,4 tok/s

CPUby processor

30322815275,80,007531.5062.259Prefill (tok/s)Generation (tok/s)AMD Ryzen 5 5600X 6-Core Processor - 174,1 tok/s Generation, 901 tok/s Prefill, TTFT 22.889 ms (6 Laufe)AMD Ryzen 5 5600X 6-C...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 101,9 tok/s Generation, 351 tok/s Prefill, TTFT 52.767 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 19,5 tok/s Generation, 339 tok/s Prefill, TTFT 80.766 ms (1 Lauf)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 236,4 tok/s Generation, 1.871 tok/s Prefill, TTFT 7.208 ms (23 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 236,4 tok/s this runAMD Ryzen 5 5600X 6-Core Processor 174,1 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 101,9 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,5 tok/s

MBby mainboard

30322815275,80,007531.5062.259Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. PRIME A520M-K - 174,1 tok/s Generation, 901 tok/s Prefill, TTFT 22.889 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 101,9 tok/s Generation, 351 tok/s Prefill, TTFT 52.767 ms (6 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 19,5 tok/s Generation, 339 tok/s Prefill, TTFT 80.766 ms (1 Lauf)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 236,4 tok/s Generation, 1.871 tok/s Prefill, TTFT 7.208 ms (23 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 236,4 tok/s this runASUSTeK COMPUTER INC. PRIME A520M-K 174,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 101,9 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 19,5 tok/s

ENGby engine

30322815275,80,001.0012.0013.002Prefill (tok/s)Generation (tok/s)unbekannt - 174,1 tok/s Generation, 628 tok/s Prefill, TTFT 13.842 ms (10 Laufe)unbekanntllama.cpp - 127,1 tok/s Generation, 526 tok/s Prefill, TTFT 42.143 ms (9 Laufe)llama.cppllm - 19,5 tok/s Generation, 339 tok/s Prefill, TTFT 80.766 ms (1 Lauf)llmvLLM - 236,4 tok/s Generation, 2.470 tok/s Prefill, TTFT 6.376 ms (16 Laufe) | DIESER LAUF★ vLLM
★ vLLM 236,4 tok/s this rununbekannt 174,1 tok/sllama.cpp 127,1 tok/sllm 19,5 tok/s

DRVby driver

30222715175,60,006331.2651.898Prefill (tok/s)Generation (tok/s)unbekannt - 236,4 tok/s Generation, 1.563 tok/s Prefill, TTFT 21.856 ms (32 Laufe)unbekanntAMD 7.0.0-27-generic - 24,4 tok/s Generation, 219 tok/s Prefill, TTFT 271 ms (4 Laufe)AMD 7.0.0-27-generic
unbekannt 236,4 tok/sAMD 7.0.0-27-generic 24,4 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 95 W
⚡ TDP 671 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)671 W estimated (TDP)GPU 600 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.20
Electricity / 1M tokensEUR 0.25
Token / kWh1.20M
Acquisition (system)EUR 11,454 full priceGPU EUR 6,000 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 14,981
Output tokens (2 years)14.05B
☁️ 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 (95 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-4-31B-it2x NVIDIA RTX A6000gemma-4-31B-it2x NVIDIA RTX A6000gemma-4-31B-itNVIDIA GeForce RTX 3090 Tigemma-4-31B-itNVIDIA GeForce RTX 3090 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.