Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaQwen (Alibaba)

Qwen2.5-3B-Instruct

Performance benchmark · measured on 16.09.2026 16:18

Benchmark-IDrun-20260918-121613-d9a298
Timebench 3 - Kombi (Prefill + Generation)Dense3BRuntime: llama.cppQuantisierung: Q4_K_M
Generation259,86tok/s
Prefill9.253,28tok/s
Time to First Token3.361,00ms
Total duration31,00s
Concurrency10parallel
Ranking in the field
613of 1214 systems

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

This run is better than 50 % of all comparable systems.
Generation 259,9 tok/s
-42 % vs Ø 450,2
Prefill 9.253,3 tok/s
+41 % vs Ø 6.556,3
Time to First Token 3.361 ms
-93 % vs Ø 47.127
Distribution in the field0 – 2.491 tok/s
Ø 450 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
Qwen2.5-3B-Instruct this run2× NVIDIA GeForce RTX 2060 · run-20260918-121613-d9a298
259,9 tok/s

Hardware

GPU: 2x NVIDIA GeForce RTX 2060 · 6 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: Qwen2.5-3B-Instruct

Configuration

benchmark-konfiguration — run-20260918-121613-d9a298
# LLM-Benchmark Konfiguration # Modell : Qwen2.5-3B-Instruct # Engine : llama.cpp # Run-ID : run-20260918-121613-d9a298 # GPU : 2x NVIDIA GeForce RTX 2060 # CPU : 4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz # RAM : 504 GB bench@llm-benchmark:~$ llama-server \ -m Qwen2.5-3B-Instruct-Q4_K_M.gguf \ -ngl 999 \ -fa on \ -c 32768 \ -np 12 \ -sm layer '(2x' RTX 2060 '6GB)'
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
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.32768
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.Qwen2.5-3B-Instruct-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
faon
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.32768
np12
Split-Mode?Verteilung ueber mehrere GPUs: none (nur eine GPU), layer (Layer aufteilen) oder row (Tensoren zeilenweise).layer

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Qwen2.5-3B-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

2862732602472346.4966.7727.0497.325Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 2060 - 259,9 tok/s Generation, 6.911 tok/s Prefill, TTFT 1.971 ms (6 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 20...
★ NVIDIA GeForce RTX 2060 259,9 tok/s this run

CPUby processor

2862732602472346.4966.7727.0497.325Prefill (tok/s)Generation (tok/s)Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 259,9 tok/s Generation, 6.911 tok/s Prefill, TTFT 1.971 ms (6 Laufe) | DIESER LAUF★ Intel(R) Xeon(R) CPU ...
★ Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 259,9 tok/s this run

MBby mainboard

2862732602472346.4966.7727.0497.325Prefill (tok/s)Generation (tok/s)Dell Inc. PowerEdge R820 - 259,9 tok/s Generation, 6.911 tok/s Prefill, TTFT 1.971 ms (6 Laufe) | DIESER LAUF★ Dell Inc. PowerEdge R...
★ Dell Inc. PowerEdge R820 259,9 tok/s this run

ENGby engine

2862732602472346.4966.7727.0497.325Prefill (tok/s)Generation (tok/s)llama.cpp - 259,9 tok/s Generation, 6.911 tok/s Prefill, TTFT 1.971 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 259,9 tok/s this run

DRVby driver

2862732602472346.4966.7727.0497.325Prefill (tok/s)Generation (tok/s)unbekannt - 259,9 tok/s Generation, 6.911 tok/s Prefill, TTFT 1.971 ms (6 Laufe)unbekannt
unbekannt 259,9 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 55 W
⚡ TDP 359 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)359 W estimated (TDP)GPU 320 + CPU 29 + Board 10 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 0.12
Token / kWh2.61M
Acquisition (system)EUR 2,445 partial priceGPU EUR 220 · CPU EUR 59 · RAM EUR 2,016 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 4,331
Output tokens (2 years)16.39B
☁️ 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 (55 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

Qwen2.5-3B-Instruct2x NVIDIA GeForce RTX 2060Qwen2.5-3B-Instruct2x NVIDIA GeForce RTX 2060
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.