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

Phi-3.5-mini-instruct

Performance benchmark · measured on 27.09.2026 03:52

Benchmark-IDrun-20260927-015654-186453
Timebench 3 - Kombi (Prefill + Generation)Dense3.8BRuntime: vLLM
Generation301,98tok/s
Prefill19.405,81tok/s
Time to First Token1.945,00ms
Total duration72,04s
Concurrency10parallel
Ranking in the field
605of 1317 systems

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

This run is better than 54 % of all comparable systems.
Generation 302,0 tok/s
-31 % vs Ø 437,7
Prefill 19.405,8 tok/s
+188 % vs Ø 6.744,5
Time to First Token 1.945 ms
-96 % vs Ø 44.397
Distribution in the field0 – 2.491 tok/s
Ø 438 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-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-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× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-0aed86
1.937,7 tok/s
Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-8db0fa
1.911,6 tok/s
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
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
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
Phi-3.5-mini-instruct this run2× AMD Radeon RX 7900 XTX · run-20260927-015654-186453
302,0 tok/s

Hardware

GPU: 2x AMD Radeon RX 7900 XTX · 24 GB VRAM
CPU: AMD Ryzen Threadripper PRO 3955WX 16-Cores
RAM: 63 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: vLLM
Quantization: -
Model: Phi-3.5-mini-instruct

Configuration

benchmark-konfiguration — run-20260927-015654-186453
# LLM-Benchmark Konfiguration # Modell : Phi-3.5-mini-instruct # Engine : vLLM # Run-ID : run-20260927-015654-186453 # GPU : 2x AMD Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 63 GB bench@llm-benchmark:~$ vllm serve microsoft/Phi-3.5-mini-instruct \ --served-model-name Phi-3.5-mini-instruct \ --tensor-parallel-size 2 \ --max-model-len 8192 '(2x' RX 7900 XTX ROCm, 'vLLM)'
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.Phi-3.5-mini-instruct
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.8192
Alias?Anzeigename des Modells nach aussen (served model name), unabhaengig vom Dateinamen.Phi-3.5-mini-instruct
Tensor-Parallel?Anzahl GPUs, auf die JEDER einzelne Modell-Layer aufgeteilt wird (Tensor-Parallelitaet). Mehr GPUs = mehr VRAM und meist mehr Speed, aber die Anzahl der Attention-Heads muss durch diesen Wert teilbar sein (z.B. 32 Heads -> nur 1, 2, 4, 8 ... moeglich, NICHT 3).2
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.8192

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Phi-3.5-mini-instruct 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

33231730228727212.87713.42513.97314.521Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 302,0 tok/s Generation, 13.699 tok/s Prefill, TTFT 1.150 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
★ AMD Radeon RX 7900 XTX 302,0 tok/s this run

CPUby processor

33231730228727212.87713.42513.97314.521Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 3955WX 16-Cores - 302,0 tok/s Generation, 13.699 tok/s Prefill, TTFT 1.150 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 302,0 tok/s this run

MBby mainboard

33231730228727212.87713.42513.97314.521Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 302,0 tok/s Generation, 13.699 tok/s Prefill, TTFT 1.150 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 302,0 tok/s this run

ENGby engine

33231730228727212.87713.42513.97314.521Prefill (tok/s)Generation (tok/s)vLLM - 302,0 tok/s Generation, 13.699 tok/s Prefill, TTFT 1.150 ms (3 Laufe) | DIESER LAUF★ vLLM
★ vLLM 302,0 tok/s this run

DRVby driver

33231730228727212.87713.42513.97314.521Prefill (tok/s)Generation (tok/s)unbekannt - 302,0 tok/s Generation, 13.699 tok/s Prefill, TTFT 1.150 ms (3 Laufe)unbekannt
unbekannt 302,0 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 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 0.20
Token / kWh1.51M
Acquisition (system)EUR 2,782 partial priceGPU EUR 2,098 · RAM EUR 504 · PSU EUR 180
Electricity (2 years)–
TCO (2 years)EUR 6,566
Output tokens (2 years)19.05B
☁️ 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

Phi-3.5-mini-instruct2x 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.