Created bymario-alka.dePowered bynoob2claw.detricoma.de
Contributed byMario AlkaGoogle

gemma-4-31B-it

Performance benchmark · measured on 27.08.2026 03:21

Benchmark-IDrun-20260827-013605-b85aa4
Timebench 3 - Kombi (Prefill + Generation)Dense31BRuntime: vLLMQuantisierung: FP8
Generation140,87tok/s
Prefill3.731,59tok/s
Time to First Token25.359,50ms
Total duration291,50s
Concurrency10parallel
Ranking in the field
1051of 1504 systems

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

This run is better than 30 % of all comparable systems.
Generation 140,9 tok/s
-69 % vs Ø 448,1
Prefill 3.731,6 tok/s
-46 % vs Ø 6.896,3
Time to First Token 25.360 ms
-42 % vs Ø 43.827
Distribution in the field0 – 3.484 tok/s
Ø 448 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 · run-20261026-180644-063abd
3.484,3 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 · run-20261026-183943-bbe82c
2.867,2 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-e28775
2.491,2 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-b37ed9
2.414,4 tok/s
gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065752-48370d
2.412,3 tok/s
NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-dce558
2.263,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065758-96fe6a
2.144,3 tok/s
gemma-4-E2B-it3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-d87c73
2.143,6 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-9c966e
1.995,4 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-8007c4
1.993,5 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20261023-065808-332d1f
1.981,1 tok/s
NVIDIA-Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
gemma-4-31B-it this runNVIDIA RTX A6000 · run-20260827-013605-b85aa4
140,9 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: 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: FP8
Model: gemma-4-31B-it

Configuration

benchmark-konfiguration — run-20260827-013605-b85aa4
# LLM-Benchmark Konfiguration # Modell : gemma-4-31B-it # Engine : vLLM # Run-ID : run-20260827-013605-b85aa4 # GPU : NVIDIA RTX A6000 # CPU : AMD Ryzen Threadripper PRO 7955WX 16-Cores # RAM : 184 GB bench@llm-benchmark:~$ vllm serve \ --model gemma-4-31B-it
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
Modellalias?Der Name, unter dem das Modell ueber die API angesprochen wird. Genau dieser Wert muss im Request-Feld 'model' stehen.gemma-4-31B-it
execution_typelocal

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

32224216180,60,001.0252.0503.075Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 108,0 tok/s Generation, 399 tok/s Prefill, TTFT 62.261 ms (3 Laufe)AMD Radeon RX 7900 XTXAMD Radeon PRO W7900 Dual Slot - 101,9 tok/s Generation, 351 tok/s Prefill, TTFT 52.767 ms (6 Laufe)AMD Radeon PRO W7900 ...NVIDIA GeForce RTX 3090 Ti - 19,5 tok/s Generation, 339 tok/s Prefill, TTFT 80.766 ms (1 Lauf)NVIDIA GeForce RTX 30...NVIDIA RTX A6000 - 251,1 tok/s Generation, 2.529 tok/s Prefill, TTFT 12.576 ms (30 Laufe) | DIESER LAUF★ NVIDIA RTX A6000
★ NVIDIA RTX A6000 251,1 tok/s this runAMD Radeon RX 7900 XTX 108,0 tok/sAMD Radeon PRO W7900 Dual Slot 101,9 tok/sNVIDIA GeForce RTX 3090 Ti 19,5 tok/s

CPUby processor

32224216180,60,001.0252.0503.075Prefill (tok/s)Generation (tok/s)Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 108,0 tok/s Generation, 399 tok/s Prefill, TTFT 62.261 ms (3 Laufe)Intel(R) Xeon(R) CPU ...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 - 251,1 tok/s Generation, 2.529 tok/s Prefill, TTFT 12.576 ms (30 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 7955WX 16-Cores 251,1 tok/s this runIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 108,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 101,9 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,5 tok/s

MBby mainboard

32224216180,60,001.0252.0503.075Prefill (tok/s)Generation (tok/s)Dell Inc. PowerEdge R820 - 108,0 tok/s Generation, 399 tok/s Prefill, TTFT 62.261 ms (3 Laufe)Dell Inc. PowerEdge R...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 - 251,1 tok/s Generation, 2.529 tok/s Prefill, TTFT 12.576 ms (30 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 251,1 tok/s this runDell Inc. PowerEdge R820 108,0 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

32224216180,60,001.4842.9694.453Prefill (tok/s)Generation (tok/s)llama.cpp - 129,2 tok/s Generation, 650 tok/s Prefill, TTFT 36.282 ms (21 Laufe)llama.cppllm - 19,5 tok/s Generation, 339 tok/s Prefill, TTFT 80.766 ms (1 Lauf)llmvLLM - 251,1 tok/s Generation, 3.640 tok/s Prefill, TTFT 6.597 ms (18 Laufe) | DIESER LAUF★ vLLM
★ vLLM 251,1 tok/s this runllama.cpp 129,2 tok/sllm 19,5 tok/s

DRVby driver

2762642512392261.8691.9482.0282.107Prefill (tok/s)Generation (tok/s)unbekannt - 251,1 tok/s Generation, 1.988 tok/s Prefill, TTFT 24.036 ms (40 Laufe)unbekannt
unbekannt 251,1 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 80 W
⚡ TDP 371 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)371 W estimated (TDP)GPU 300 + CPU 46 + Board 25 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 0.22
Token / kWh1.37M
Acquisition (system)EUR 8,424 full priceGPU EUR 3,000 · CPU EUR 1,399 · Board EUR 1,299 · RAM EUR 2,576 · PSU EUR 150
Electricity (2 years)–
TCO (2 years)EUR 10,374
Output tokens (2 years)8.88B
☁️ 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 (80 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-itNVIDIA RTX A6000gemma-4-31B-it2x NVIDIA RTX A6000gemma-4-31B-it2x NVIDIA RTX A6000gemma-4-31B-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)––––

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.