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

gemma-4-31B-it

Performance benchmark · measured on 30.07.2026 07:32

Benchmark-IDrun-20260730-084906-8acd83
Timebench 3 - Kombi (Prefill + Generation)Dense31BRuntime: llama.cppQuantisierung: Q4_K_M
Generation62,77tok/s
Prefill1.935,48tok/s
Time to First Token1.023,00ms
Total duration34,67s
Concurrency1parallel
Ranking in the field
120of 139 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 14 % of all comparable systems.
Generation 62,8 tok/s
-64 % vs Ø 176,8
Prefill 1.935,5 tok/s
-59 % vs Ø 4.723,6
Time to First Token 1.023 ms
+20 % vs Ø 852
Distribution in the field12 – 362 tok/s
Ø 177 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-ac388e
362,3 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-5e5085
361,4 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-a2f36d
356,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-1be57b
355,6 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032120-b63d5d
350,7 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-74868e
350,0 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-120dc2
348,9 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184455-9cb45c
343,9 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105339-e213a2
331,0 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-e34cf0
330,8 tok/s
Nemotron-Cascade-2-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-3ddb51
330,2 tok/s
Nemotron-3-Nano-Omni-30B-A3B-Reasoning3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105339-133b6a
330,1 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105341-f734f1
330,0 tok/s
Nemotron-Cascade-2-30B-A3B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-105340-508364
329,9 tok/s
gemma-4-31B-it this run3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260730-084906-8acd83
62,8 tok/s

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× concurrent · Generation (tok/s)

Hardware

GPU: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

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

Configuration

benchmark-konfiguration — run-20260730-084906-8acd83
# LLM-Benchmark Konfiguration # Modell : gemma-4-31B-it # Engine : llama.cpp # Run-ID : run-20260730-084906-8acd83 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--ReadyArt--gemma-4-31B-it-scotoma-GGUF/snapshots/273b4b513d43680abdad00a219bc938032547f12/gemma-4-31B-scotoma-Q4_K_M.gguf \ --alias gemma-4-31B-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-4-31B-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--ReadyArt--gemma-4-31B-it-scotoma-GGUF/snapshots/273b4b513d43680abdad00a219bc938032547f12/gemma-4-31B-scotoma-Q4_K_M.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-4-31B-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

6024523011510,008181.6372.455Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 466,1 tok/s Generation, 1.824 tok/s Prefill, TTFT 12.692 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 438,4 tok/s Generation, 1.252 tok/s Prefill, TTFT 16.071 ms (6 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 5070 Ti - 42,0 tok/s Generation, 364 tok/s Prefill, TTFT 71.670 ms (6 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 3090 Ti - 19,5 tok/s Generation, 345 tok/s Prefill, TTFT 88.782 ms (6 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 397,5 tok/s Generation, 2.030 tok/s Prefill, TTFT 14.272 ms (24 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 466,1 tok/sNVIDIA GeForce RTX 5090 438,4 tok/s★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 397,5 tok/s this runNVIDIA GeForce RTX 5070 Ti 42,0 tok/sNVIDIA GeForce RTX 3090 Ti 19,5 tok/s

CPUby processor

6024523011510,008181.6372.455Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 466,1 tok/s Generation, 1.824 tok/s Prefill, TTFT 12.692 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 438,4 tok/s Generation, 1.252 tok/s Prefill, TTFT 16.071 ms (6 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 42,0 tok/s Generation, 364 tok/s Prefill, TTFT 71.670 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 19,5 tok/s Generation, 345 tok/s Prefill, TTFT 88.782 ms (6 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 397,5 tok/s Generation, 2.030 tok/s Prefill, TTFT 14.272 ms (24 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 466,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 438,4 tok/s★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 397,5 tok/s this runAMD Ryzen Threadripper PRO 5975WX 32-Cores 42,0 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 19,5 tok/s

MBby mainboard

6024523011510,008181.6372.455Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 466,1 tok/s Generation, 1.824 tok/s Prefill, TTFT 12.692 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 438,4 tok/s Generation, 1.252 tok/s Prefill, TTFT 16.071 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 42,0 tok/s Generation, 364 tok/s Prefill, TTFT 71.670 ms (6 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 19,5 tok/s Generation, 345 tok/s Prefill, TTFT 88.782 ms (6 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 397,5 tok/s Generation, 2.030 tok/s Prefill, TTFT 14.272 ms (24 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 466,1 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 438,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 397,5 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 42,0 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 19,5 tok/s

ENGby engine

5134894664434201.3991.4581.5181.577Prefill (tok/s)Generation (tok/s)llama.cpp - 466,1 tok/s Generation, 1.488 tok/s Prefill, TTFT 30.788 ms (48 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 466,1 tok/s this run

DRVby driver

5134894664434201.3991.4581.5181.577Prefill (tok/s)Generation (tok/s)unbekannt - 466,1 tok/s Generation, 1.488 tok/s Prefill, TTFT 30.788 ms (48 Laufe)unbekannt
unbekannt 466,1 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× 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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 1.30
Token / kWh230.00K
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)3.96B
☁️ 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 (165 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-it3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Editiongemma-4-31B-itNVIDIA GeForce RTX 5090gemma-4-31B-itNVIDIA GeForce RTX 5090gemma-4-31B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition
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.