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

Qwen2.5-32B-Instruct-AWQ

Performance benchmark · measured on 26.09.2026 19:22

Benchmark-IDrun-20260926-175013-3b5e4b
Timebench 3 - Kombi (Prefill + Generation)Dense32BRuntime: vLLMQuantisierung: AWQ
Generation179,02tok/s
Prefill3.915,25tok/s
Time to First Token10.289,50ms
Total duration136,24s
Concurrency10parallel
Ranking in the field
31of 38 systems

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

This run is better than 19 % of all comparable systems.
Generation 179,0 tok/s
-38 % vs Ø 291,0
Prefill 3.915,3 tok/s
-28 % vs Ø 5.406,8
Time to First Token 10.290 ms
-37 % vs Ø 16.214
Distribution in the field110 – 469 tok/s
Ø 291 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: 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: AWQ
Model: Qwen2.5-32B-Instruct-AWQ

Configuration

benchmark-konfiguration — run-20260926-175013-3b5e4b
# LLM-Benchmark Konfiguration # Modell : Qwen2.5-32B-Instruct-AWQ # Engine : vLLM # Run-ID : run-20260926-175013-3b5e4b # GPU : 2x AMD Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 63 GB bench@llm-benchmark:~$ vllm serve Qwen/Qwen2.5-32B-Instruct-AWQ \ --served-model-name Qwen2.5-32B-Instruct \ --tensor-parallel-size 2 \ --max-model-len 8192 \ --quantization awq '(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.Qwen2.5-32B-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.Qwen2.5-32B-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
Quantisierung?Quantisierungsverfahren der Gewichte (z.B. awq, gptq, fp8, bitsandbytes). Verkleinert das Modell und spart VRAM, kann die Genauigkeit leicht senken. Leer = keine zusaetzliche Quantisierung.awq

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Qwen2.5-32B-Instruct-AWQ 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

6544913271640,001.8623.7245.587Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 510,3 tok/s Generation, 4.510 tok/s Prefill, TTFT 5.988 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 473,9 tok/s Generation, 4.532 tok/s Prefill, TTFT 9.919 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 412,6 tok/s Generation, 4.568 tok/s Prefill, TTFT 11.783 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX A6000 - 362,6 tok/s Generation, 4.063 tok/s Prefill, TTFT 4.052 ms (9 Laufe)NVIDIA RTX A6000NVIDIA GeForce RTX 3090 Ti - 223,8 tok/s Generation, 2.049 tok/s Prefill, TTFT 20.233 ms (6 Laufe)NVIDIA GeForce RTX 30...AMD Radeon AI PRO R9700 - 116,3 tok/s Generation, 430 tok/s Prefill, TTFT 108.658 ms (13 Laufe)AMD Radeon AI PRO R97...AMD Radeon PRO W7900 Dual Slot - 89,6 tok/s Generation, 1.013 tok/s Prefill, TTFT 13.903 ms (3 Laufe)AMD Radeon PRO W7900 ...AMD Radeon PRO W7800 48GB - 69,9 tok/s Generation, 1.608 tok/s Prefill, TTFT 9.864 ms (3 Laufe)AMD Radeon PRO W7800 ...NVIDIA GeForce RTX 5070 Ti - 45,0 tok/s Generation, 619 tok/s Prefill, TTFT 95.102 ms (3 Laufe)NVIDIA GeForce RTX 50...AMD Radeon RX 7900 XTX - 179,0 tok/s Generation, 2.823 tok/s Prefill, TTFT 5.787 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 510,3 tok/sNVIDIA GeForce RTX 5090 473,9 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 412,6 tok/sNVIDIA RTX A6000 362,6 tok/sNVIDIA GeForce RTX 3090 Ti 223,8 tok/s★ AMD Radeon RX 7900 XTX 179,0 tok/s this runAMD Radeon AI PRO R9700 116,3 tok/sAMD Radeon PRO W7900 Dual Slot 89,6 tok/sAMD Radeon PRO W7800 48GB 69,9 tok/sNVIDIA GeForce RTX 5070 Ti 45,0 tok/s

CPUby processor

6464843231610,01781.9423.7065.470Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 510,3 tok/s Generation, 4.510 tok/s Prefill, TTFT 5.988 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 473,9 tok/s Generation, 4.532 tok/s Prefill, TTFT 9.919 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 412,6 tok/s Generation, 4.568 tok/s Prefill, TTFT 11.783 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 362,6 tok/s Generation, 1.991 tok/s Prefill, TTFT 74.758 ms (19 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 223,8 tok/s Generation, 2.049 tok/s Prefill, TTFT 20.233 ms (6 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 3 3100 4-Core Processor - 116,3 tok/s Generation, 1.438 tok/s Prefill, TTFT 9.543 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 89,6 tok/s Generation, 1.080 tok/s Prefill, TTFT 39.623 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 179,0 tok/s Generation, 2.823 tok/s Prefill, TTFT 5.787 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 510,3 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 473,9 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 412,6 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 362,6 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 223,8 tok/s★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 179,0 tok/s this runAMD Ryzen 3 3100 4-Core Processor 116,3 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 89,6 tok/s

MBby mainboard

6404803201600,06092.1933.7775.361Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 510,3 tok/s Generation, 4.510 tok/s Prefill, TTFT 5.988 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 473,9 tok/s Generation, 4.532 tok/s Prefill, TTFT 9.919 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 412,6 tok/s Generation, 2.820 tok/s Prefill, TTFT 54.516 ms (28 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 223,8 tok/s Generation, 2.049 tok/s Prefill, TTFT 20.233 ms (6 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 116,3 tok/s Generation, 1.438 tok/s Prefill, TTFT 9.543 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 179,0 tok/s Generation, 1.516 tok/s Prefill, TTFT 31.164 ms (12 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 510,3 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 473,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 412,6 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 223,8 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 179,0 tok/s this runASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 116,3 tok/s

ENGby engine

5695304924544161.8472.5463.2453.944Prefill (tok/s)Generation (tok/s)llama.cpp - 474,0 tok/s Generation, 2.280 tok/s Prefill, TTFT 50.612 ms (40 Laufe)llama.cppvLLM - 510,3 tok/s Generation, 3.512 tok/s Prefill, TTFT 5.091 ms (18 Laufe) | DIESER LAUF★ vLLM
★ vLLM 510,3 tok/s this runllama.cpp 474,0 tok/s

DRVby driver

5615365104854592.5022.6092.7152.822Prefill (tok/s)Generation (tok/s)unbekannt - 510,3 tok/s Generation, 2.662 tok/s Prefill, TTFT 36.485 ms (58 Laufe)unbekannt
unbekannt 510,3 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 0.34
Token / kWh895.10K
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)11.29B
☁️ 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

Qwen2.5-32B-Instruct-AWQ2x AMD Radeon RX 7900 XTXQwen2.5-32B-Instruct-AWQNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen2.5-32B-Instruct-AWQNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen2.5-32B-Instruct-AWQNVIDIA GeForce RTX 5090
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.