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

gemma-4-31B-it

Performance benchmark · measured on 08.10.2026 12:16

Benchmark-IDrun-20261009-081231-c9c8af
Timebench 3 - Kombi (Prefill + Generation)Dense31BRuntime: llama.cppQuantisierung: Q4_K_M
ℹ
Public note: Dell PowerEdge R820 . 2x AMD Radeon RX 7900 XTX (48 GB VRAM gesamt, ROCm/HIP) . RAM: 32x 16 GB SK Hynix DDR3-1600 ECC RDIMM (HMT42GR7AFR4A-PB) = 512 GB @ 1600 MT/s
Generation108,03tok/s
Prefill120,86tok/s
Time to First Token163.656,50ms
Total duration518,29s
Concurrency10parallel
Ranking in the field
1072of 1427 systems

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

This run is better than 25 % of all comparable systems.
Generation 108,0 tok/s
-75 % vs Ø 425,3
Prefill 120,9 tok/s
-98 % vs Ø 6.659,3
Time to First Token 163.657 ms
+257 % vs Ø 45.848
Distribution in the field0 – 2.491 tok/s
Ø 425 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

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
Nemotron-3.5-Lightning-30B-A3BNVIDIA GeForce RTX 3090 Ti · run-20261021-093815-dce558
2.263,7 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 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
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-e0eafd
1.897,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-7c961d
1.890,7 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd
1.878,7 tok/s
gpt-oss-20b3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b
1.835,7 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046
1.830,3 tok/s
gemma-4-31B-it this run2× 2x AMD Radeon RX 7900 XTX · run-20261009-081231-c9c8af
108,0 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz
RAM: 504 GB
Mainboard: Dell Inc. PowerEdge R820

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: gemma-4-31B-it

Configuration

benchmark-konfiguration — run-20261009-081231-c9c8af
# LLM-Benchmark Konfiguration # Modell : gemma-4-31B-it # Engine : llama.cpp # Run-ID : run-20261009-081231-c9c8af # GPU : 2x AMD Radeon RX 7900 XTX # CPU : 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz # RAM : 504 GB bench@llm-benchmark:~$ llama-server \ -m google_gemma-4-31B-it-IQ4_XS.gguf \ --alias gemma-4-31B-it \ -ngl 999 \ -sm layer \ -fa on \ -c 40960 \ -np 10 '(2x' RX 7900 XTX ROCm/HIP, 'gpu)'
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-4-31B-it
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.40960
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.google_gemma-4-31B-it-IQ4_XS.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
Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise).layer
faon
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.40960
np10
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

32224116180,40,001.0322.0653.097Prefill (tok/s)Generation (tok/s)NVIDIA RTX A6000 - 251,1 tok/s Generation, 2.529 tok/s Prefill, TTFT 12.576 ms (30 Laufe)NVIDIA RTX A6000NVIDIA 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...AMD Radeon RX 7900 XTX - 108,0 tok/s Generation, 399 tok/s Prefill, TTFT 62.261 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
NVIDIA RTX A6000 251,1 tok/sNVIDIA GeForce RTX 3090 Ti 174,1 tok/s★ AMD Radeon RX 7900 XTX 108,0 tok/s this runAMD Radeon PRO W7900 Dual Slot 101,9 tok/sAMD Radeon AI PRO R9700 24,4 tok/s

CPUby processor

32224216180,60,008241.6482.472Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 251,1 tok/s Generation, 2.043 tok/s Prefill, TTFT 9.985 ms (38 Laufe)AMD Ryzen Threadrippe...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...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) | DIESER LAUF★ Intel(R) Xeon(R) CPU ...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 251,1 tok/sAMD Ryzen 5 5600X 6-Core Processor 174,1 tok/s★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 108,0 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 101,9 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,5 tok/s

MBby mainboard

32224216180,60,008241.6482.472Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 251,1 tok/s Generation, 2.043 tok/s Prefill, TTFT 9.985 ms (38 Laufe)ASUSTeK COMPUTER INC....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...Dell Inc. PowerEdge R820 - 108,0 tok/s Generation, 399 tok/s Prefill, TTFT 62.261 ms (3 Laufe) | DIESER LAUF★ Dell Inc. PowerEdge R...
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 251,1 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 174,1 tok/s★ Dell Inc. PowerEdge R820 108,0 tok/s this runASUSTeK 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

32224216180,60,001.2272.4543.682Prefill (tok/s)Generation (tok/s)vLLM - 251,1 tok/s Generation, 3.018 tok/s Prefill, TTFT 5.447 ms (22 Laufe)vLLMunbekannt - 174,1 tok/s Generation, 628 tok/s Prefill, TTFT 13.842 ms (10 Laufe)unbekanntllm - 19,5 tok/s Generation, 339 tok/s Prefill, TTFT 80.766 ms (1 Lauf)llmllama.cpp - 129,2 tok/s Generation, 650 tok/s Prefill, TTFT 36.282 ms (21 Laufe) | DIESER LAUF★ llama.cpp
vLLM 251,1 tok/sunbekannt 174,1 tok/s★ llama.cpp 129,2 tok/s this runllm 19,5 tok/s

DRVby driver

32224116180,40,006961.3922.089Prefill (tok/s)Generation (tok/s)unbekannt - 251,1 tok/s Generation, 1.716 tok/s Prefill, TTFT 21.997 ms (50 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 251,1 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 35 W
⚡ TDP 749 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)749 W estimated (TDP)GPU 710 + CPU 29 + Board 10 W full load
Avg cost / hourEUR 0.22
Electricity / 1M tokensEUR 0.58
Token / kWh519.41K
Acquisition (system)EUR 4,353 partial priceGPU EUR 2,098 · CPU EUR 59 · RAM EUR 2,016 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 8,288
Output tokens (2 years)6.81B
☁️ 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 (35 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 AMD Radeon RX 7900 XTXgemma-4-31B-it2x NVIDIA RTX A6000gemma-4-31B-it2x NVIDIA RTX A6000gemma-4-31B-it2x NVIDIA RTX A6000
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.