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

Qwen2.5-7B-Instruct

Performance benchmark · measured on 22.09.2026 09:11

Benchmark-IDrun-20260922-074333-aa002a
Timebench 3 - Kombi (Prefill + Generation)Dense7BRuntime: llama.cppQuantisierung: Q8_0
Generation250,57tok/s
Prefill9.085,20tok/s
Time to First Token3.441,50ms
Total duration94,41s
Concurrency10parallel
Ranking in the field
33of 234 systems

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

This run is better than 86 % of all comparable systems.
Generation 250,6 tok/s
+79 % vs Ø 139,6
Prefill 9.085,2 tok/s
+225 % vs Ø 2.798,0
Time to First Token 3.442 ms
-97 % vs Ø 101.035
Distribution in the field0 – 667 tok/s
Ø 140 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

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

Hardware

GPU: AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen 3 3100 4-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING

Setup

Runtime: llama.cpp
Quantization: Q8_0
Model: Qwen2.5-7B-Instruct

Configuration

benchmark-konfiguration — run-20260922-074333-aa002a
# LLM-Benchmark Konfiguration # Modell : Qwen2.5-7B-Instruct # Engine : llama.cpp # Run-ID : run-20260922-074333-aa002a # GPU : AMD Radeon AI PRO R9700 # CPU : AMD Ryzen 3 3100 4-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/models/qwen2.5-7b-instruct-q8_0-00001-of-00003.gguf \ --alias Qwen2.5-7B-Instruct \ -ngl 999 \ -fa on \ -c 49152 \ -np 12 '(AMD' Radeon AI PRO R9700, ROCm 7.2.4, 'HIP_VISIBLE_DEVICES=0)'
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.Qwen2.5-7B-Instruct
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.49152
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/models/qwen2.5-7b-instruct-q8_0-00001-of-00003.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.49152
np12

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Qwen2.5-7B-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

2942502051611172.7264.3185.9117.503Prefill (tok/s)Generation (tok/s)NVIDIA GeForce RTX 2060 - 160,3 tok/s Generation, 3.649 tok/s Prefill, TTFT 3.816 ms (3 Laufe)NVIDIA GeForce RTX 20...AMD Radeon AI PRO R9700 - 250,6 tok/s Generation, 6.580 tok/s Prefill, TTFT 2.039 ms (3 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
★ AMD Radeon AI PRO R9700 250,6 tok/s this runNVIDIA GeForce RTX 2060 160,3 tok/s

CPUby processor

2942502051611172.7264.3185.9117.503Prefill (tok/s)Generation (tok/s)Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 160,3 tok/s Generation, 3.649 tok/s Prefill, TTFT 3.816 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen 3 3100 4-Core Processor - 250,6 tok/s Generation, 6.580 tok/s Prefill, TTFT 2.039 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 3 3100 4-Co...
★ AMD Ryzen 3 3100 4-Core Processor 250,6 tok/s this runIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 160,3 tok/s

MBby mainboard

2942502051611172.7264.3185.9117.503Prefill (tok/s)Generation (tok/s)Dell Inc. PowerEdge R820 - 160,3 tok/s Generation, 3.649 tok/s Prefill, TTFT 3.816 ms (3 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 250,6 tok/s Generation, 6.580 tok/s Prefill, TTFT 2.039 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 250,6 tok/s this runDell Inc. PowerEdge R820 160,3 tok/s

ENGby engine

2762632512382264.8085.0125.2175.421Prefill (tok/s)Generation (tok/s)llama.cpp - 250,6 tok/s Generation, 5.114 tok/s Prefill, TTFT 2.927 ms (6 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 250,6 tok/s this run

DRVby driver

2762632512382264.8085.0125.2175.421Prefill (tok/s)Generation (tok/s)unbekannt - 250,6 tok/s Generation, 5.114 tok/s Prefill, TTFT 2.927 ms (6 Laufe)unbekannt
unbekannt 250,6 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 20 W
⚡ TDP 300 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)300 W estimated (TDP)GPU 300 W full load
Avg cost / hourEUR 0.090
Electricity / 1M tokensEUR 0.100
Token / kWh3.01M
Acquisition (system)EUR 1,520 partial priceGPU EUR 1,400 · PSU EUR 120
Electricity (2 years)
TCO (2 years)EUR 3,097
Output tokens (2 years)15.80B
☁️ 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 (20 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

Qwen2.5-7B-InstructAMD Radeon AI PRO R9700Qwen2.5-7B-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.