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

Step-3.5-Flash

Performance benchmark · measured on 29.07.2026 04:07

Benchmark-IDrun-20260729-060801-a93ded
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cpp
Generation7,94tok/s
Prefill87,07tok/s
Time to First Token104.394,00ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
321of 346 systems

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

This run is better than 7 % of all comparable systems.
Generation 7,9 tok/s
-99 % vs Ø 651,3
Prefill 87,1 tok/s
-99 % vs Ø 6.626,4
Time to First Token 104.394 ms
+153 % vs Ø 41.299
Distribution in the field0 – 2.491 tok/s
Ø 651 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
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-4cca42
2.182,7 tok/s
gemma-4-E2B-it3× 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-20260728-140954-8007c4
1.993,5 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
NVIDIA-Nemotron-3-Nano-4B3× 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
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-2ed9dd
1.878,7 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-26063b
1.835,7 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-a77046
1.830,3 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-c6e7e0
1.819,5 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-2b99aa
1.802,0 tok/s
Step-3.5-Flash this runNVIDIA GeForce RTX 5090 · run-20260729-060801-a93ded
7,9 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA GeForce RTX 5090 · 32 GB VRAM
CPU: AMD Ryzen 7 5800X3D 8-Core Processor
RAM: 126 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING

Setup

Runtime: llama.cpp
Quantization: -
Model: Step-3.5-Flash

Configuration

benchmark-konfiguration — run-20260729-060801-a93ded
# LLM-Benchmark Konfiguration # Modell : Step-3.5-Flash # Engine : llama.cpp # Run-ID : run-20260729-060801-a93ded # GPU : NVIDIA GeForce RTX 5090 # CPU : AMD Ryzen 7 5800X3D 8-Core Processor # RAM : 126 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--stepfun-ai--Step-3.5-Flash-GGUF-Q4_K_S/snapshots/6930492fee9ffd6f13c2e665a94244c60d2d7d83/step3p5_flash_Q4_K_S-00001-of-00012.gguf \ --alias Step-3.5-Flash \ --host 0.0.0.0 \ --port 8000 \ -ngl 12 \ -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.Step-3.5-Flash
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./root/.cache/huggingface/hub/models--stepfun-ai--Step-3.5-Flash-GGUF-Q4_K_S/snapshots/6930492fee9ffd6f13c2e665a94244c60d2d7d83/step3p5_flash_Q4_K_S-00001-of-00012.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.12
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

Step-3.5-Flash 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

9587194792400,009711.9412.912Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 739,1 tok/s Generation, 2.361 tok/s Prefill, TTFT 19.901 ms (12 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 45,5 tok/s Generation, 174 tok/s Prefill, TTFT 129.867 ms (3 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon AI PRO R9700 - 31,6 tok/s Generation, 298 tok/s Prefill, TTFT 54.060 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5090 - 13,8 tok/s Generation, 86 tok/s Prefill, TTFT 111.357 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 739,1 tok/sNVIDIA RTX PRO 6000 Blackwell Workstation Edition 45,5 tok/sAMD Radeon AI PRO R9700 31,6 tok/s★ NVIDIA GeForce RTX 5090 13,8 tok/s this run

CPUby processor

9587194792400,009711.9412.912Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 9965WX 24-Cores - 739,1 tok/s Generation, 2.361 tok/s Prefill, TTFT 19.901 ms (12 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 45,5 tok/s Generation, 174 tok/s Prefill, TTFT 129.867 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 31,6 tok/s Generation, 298 tok/s Prefill, TTFT 54.060 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 7 5800X3D 8-Core Processor - 13,8 tok/s Generation, 86 tok/s Prefill, TTFT 111.357 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 7 5800X3D 8...
AMD Ryzen Threadripper PRO 9965WX 24-Cores 739,1 tok/sAMD Ryzen 9 9950X 16-Core Processor 45,5 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 31,6 tok/s★ AMD Ryzen 7 5800X3D 8-Core Processor 13,8 tok/s this run

MBby mainboard

9587194792400,008491.6982.547Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 739,1 tok/s Generation, 2.066 tok/s Prefill, TTFT 24.780 ms (14 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 45,5 tok/s Generation, 174 tok/s Prefill, TTFT 129.867 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 13,8 tok/s Generation, 86 tok/s Prefill, TTFT 111.357 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 739,1 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 45,5 tok/s★ ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 13,8 tok/s this run

ENGby engine

8137767397026651.3961.4561.5151.575Prefill (tok/s)Generation (tok/s)llama.cpp - 739,1 tok/s Generation, 1.485 tok/s Prefill, TTFT 53.530 ms (20 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 739,1 tok/s this run

DRVby driver

8137767397026651.3961.4561.5151.575Prefill (tok/s)Generation (tok/s)unbekannt - 739,1 tok/s Generation, 1.485 tok/s Prefill, TTFT 53.530 ms (20 Laufe)unbekannt
unbekannt 739,1 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 72 W
⚡ TDP 622 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)622 W estimated (TDP)GPU 575 + CPU 35 + Board 12 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 6.52
Token / kWh45.99K
Acquisition (system)EUR 4,986 full priceGPU EUR 3,300 · CPU EUR 349 · Board EUR 149 · RAM EUR 1,008 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 8,253
Output tokens (2 years)500.79M
☁️ 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 (72 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

Step-3.5-FlashNVIDIA GeForce RTX 5090Step-3.5-Flash3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionStep-3.5-Flash3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionStep-3.5-Flash3x NVIDIA RTX PRO 6000 Blackwell Max-Q 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.