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

Step-3.5-Flash

Performance benchmark · measured on 30.09.2026 18:11

Benchmark-IDrun-20260930-163153-abf239
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: Q4_K_M
Generation16,78tok/s
Prefill164,68tok/s
Time to First Token73.137,00ms
Total duration355,78s
Concurrency5parallel
Ranking in the field
1237of 1360 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 9 % of all comparable systems.
Generation 16,8 tok/s
-93 % vs Ø 253,1
Prefill 164,7 tok/s
-97 % vs Ø 5.451,5
Time to First Token 73.137 ms
+155 % vs Ø 28.715
Distribution in the field0 – 1.349 tok/s
Ø 253 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d
1.349,3 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-5b4937
1.301,9 tok/s
gemma-4-E2B-it3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-4111a9
1.195,7 tok/s
Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-5432cd
1.164,8 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9
1.136,3 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260730-035052-09627f
1.135,0 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31
1.113,5 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91
1.090,6 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818
1.071,0 tok/s
Nemotron-3-Nano-4B3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92
1.051,1 tok/s
gpt-oss-20b3× 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a
1.015,5 tok/s
Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
Step-3.5-Flash this run2× 2x AMD Radeon RX 7900 XTX · run-20260930-163153-abf239
16,8 tok/s

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: AMD Ryzen Threadripper PRO 3955WX 16-Cores
RAM: 189 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Step-3.5-Flash

Configuration

benchmark-konfiguration — run-20260930-163153-abf239
# LLM-Benchmark Konfiguration # Modell : Step-3.5-Flash # Engine : llama.cpp # Run-ID : run-20260930-163153-abf239 # GPU : 2x AMD Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 189 GB bench@llm-benchmark:~$ llama-server \ -m stepfun-ai_Step-3.5-Flash-Q4_K_M-00001-of-00004.gguf \ --alias Step-3.5-Flash mode=moe \ -c 24576 \ -np 10 '(2x' RX 7900 XTX + 196GB RAM 'Offload)'
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.24576
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.stepfun-ai_Step-3.5-Flash-Q4_K_M-00001-of-00004.gguf
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.24576
np10
execution_typelocal

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

18,517,616,815,915,1151158164171Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 16,8 tok/s Generation, 161 tok/s Prefill, TTFT 74.043 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
★ AMD Radeon RX 7900 XTX 16,8 tok/s this run

CPUby processor

18,517,616,815,915,1151158164171Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 3955WX 16-Cores - 16,8 tok/s Generation, 161 tok/s Prefill, TTFT 74.043 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 16,8 tok/s this run

MBby mainboard

18,517,616,815,915,1151158164171Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 16,8 tok/s Generation, 161 tok/s Prefill, TTFT 74.043 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 16,8 tok/s this run

ENGby engine

18,517,616,815,915,1151158164171Prefill (tok/s)Generation (tok/s)llama.cpp - 16,8 tok/s Generation, 161 tok/s Prefill, TTFT 74.043 ms (3 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 16,8 tok/s this run

DRVby driver

18,517,616,815,915,1151158164171Prefill (tok/s)Generation (tok/s)unbekannt - 16,8 tok/s Generation, 161 tok/s Prefill, TTFT 74.043 ms (3 Laufe)unbekannt
unbekannt 16,8 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (5× 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 10 W
⚡ TDP 720 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)720 W estimated (TDP)GPU 710 + Board 10 W full load
Avg cost / hourEUR 0.22
Electricity / 1M tokensEUR 3.58
Token / kWh83.90K
Acquisition (system)EUR 3,790 partial priceGPU EUR 2,098 · RAM EUR 1,512 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 7,574
Output tokens (2 years)1.06B
☁️ 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 (10 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-Flash2x 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.