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

Qwen2.5-Coder-32B-Instruct

Performance benchmark · measured on 27.09.2026 04:04

Benchmark-IDrun-20260927-023029-76da43
Timebench 3 - Kombi (Prefill + Generation)Dense32BRuntime: vLLMQuantisierung: AWQ
Generation21,09tok/s
Prefill1.399,28tok/s
Time to First Token1.754,50ms
Total duration100,62s
Concurrency1parallel
Ranking in the field
1270of 1684 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 25 % of all comparable systems.
Generation 21,1 tok/s
-73 % vs Ø 78,5
Prefill 1.399,3 tok/s
-52 % vs Ø 2.894,0
Time to First Token 1.755 ms
-93 % vs Ø 25.628
Distribution in the field0 – 405 tok/s
Ø 78 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× 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-Coder-32B-Instruct

Configuration

benchmark-konfiguration — run-20260927-023029-76da43
# LLM-Benchmark Konfiguration # Modell : Qwen2.5-Coder-32B-Instruct # Engine : vLLM # Run-ID : run-20260927-023029-76da43 # 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-Coder-32B-Instruct-AWQ \ --served-model-name Qwen2.5-Coder-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-Coder-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-Coder-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-Coder-32B-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

6504883251630,001.8473.6935.540Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 500,6 tok/s Generation, 4.446 tok/s Prefill, TTFT 6.330 ms (6 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 479,6 tok/s Generation, 4.242 tok/s Prefill, TTFT 10.075 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 412,8 tok/s Generation, 4.476 tok/s Prefill, TTFT 11.913 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA RTX A6000 - 362,6 tok/s Generation, 3.377 tok/s Prefill, TTFT 5.996 ms (27 Laufe)NVIDIA RTX A6000NVIDIA GeForce RTX 3090 Ti - 236,4 tok/s Generation, 2.040 tok/s Prefill, TTFT 20.899 ms (3 Laufe)NVIDIA GeForce RTX 30...AMD Radeon AI PRO R9700 - 115,0 tok/s Generation, 2.531 tok/s Prefill, TTFT 46.208 ms (30 Laufe)AMD Radeon AI PRO R97...AMD Radeon PRO W7900 Dual Slot - 102,1 tok/s Generation, 1.068 tok/s Prefill, TTFT 13.870 ms (12 Laufe)AMD Radeon PRO W7900 ...AMD Radeon PRO W7800 48GB - 69,8 tok/s Generation, 1.503 tok/s Prefill, TTFT 9.917 ms (3 Laufe)AMD Radeon PRO W7800 ...NVIDIA GeForce RTX 5070 Ti - 45,3 tok/s Generation, 587 tok/s Prefill, TTFT 95.842 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA GeForce RTX 2060 - 2,3 tok/s Generation, 53 tok/s Prefill, TTFT 145.743 ms (2 Laufe)NVIDIA GeForce RTX 20...AMD Radeon RX 7900 XTX - 178,5 tok/s Generation, 2.706 tok/s Prefill, TTFT 6.031 ms (3 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 500,6 tok/sNVIDIA GeForce RTX 5090 479,6 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 412,8 tok/sNVIDIA RTX A6000 362,6 tok/sNVIDIA GeForce RTX 3090 Ti 236,4 tok/s★ AMD Radeon RX 7900 XTX 178,5 tok/s this runAMD Radeon AI PRO R9700 115,0 tok/sAMD Radeon PRO W7900 Dual Slot 102,1 tok/sAMD Radeon PRO W7800 48GB 69,8 tok/sNVIDIA GeForce RTX 5070 Ti 45,3 tok/sNVIDIA GeForce RTX 2060 2,3 tok/s

CPUby processor

6504883251630,001.8473.6935.540Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 500,6 tok/s Generation, 4.446 tok/s Prefill, TTFT 6.330 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 7 5800X3D 8-Core Processor - 479,6 tok/s Generation, 4.242 tok/s Prefill, TTFT 10.075 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 412,8 tok/s Generation, 4.476 tok/s Prefill, TTFT 11.913 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 362,6 tok/s Generation, 3.013 tok/s Prefill, TTFT 28.140 ms (54 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 236,4 tok/s Generation, 2.040 tok/s Prefill, TTFT 20.899 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen 3 3100 4-Core Processor - 115,0 tok/s Generation, 1.467 tok/s Prefill, TTFT 9.524 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 102,1 tok/s Generation, 1.060 tok/s Prefill, TTFT 26.873 ms (18 Laufe)AMD Ryzen Threadrippe...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 2,3 tok/s Generation, 53 tok/s Prefill, TTFT 145.743 ms (2 Laufe)Intel(R) Xeon(R) CPU ...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 178,5 tok/s Generation, 2.706 tok/s Prefill, TTFT 6.031 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 500,6 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 479,6 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 412,8 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 362,6 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 236,4 tok/s★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 178,5 tok/s this runAMD Ryzen 3 3100 4-Core Processor 115,0 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 102,1 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 2,3 tok/s

MBby mainboard

6504883251630,001.8343.6695.503Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 500,6 tok/s Generation, 4.446 tok/s Prefill, TTFT 6.330 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 479,6 tok/s Generation, 4.242 tok/s Prefill, TTFT 10.075 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 412,8 tok/s Generation, 3.222 tok/s Prefill, TTFT 25.822 ms (63 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 236,4 tok/s Generation, 2.040 tok/s Prefill, TTFT 20.899 ms (3 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 115,0 tok/s Generation, 1.467 tok/s Prefill, TTFT 9.524 ms (3 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 2,3 tok/s Generation, 53 tok/s Prefill, TTFT 145.743 ms (2 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 178,5 tok/s Generation, 1.296 tok/s Prefill, TTFT 23.896 ms (21 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 500,6 tok/sASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 479,6 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 412,8 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 236,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 178,5 tok/s this runASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 115,0 tok/sDell Inc. PowerEdge R820 2,3 tok/s

ENGby engine

6474853231620,01.3142.4163.5194.622Prefill (tok/s)Generation (tok/s)llama.cpp - 479,6 tok/s Generation, 1.928 tok/s Prefill, TTFT 41.923 ms (58 Laufe)llama.cppunbekannt - 21,2 tok/s Generation, 3.615 tok/s Prefill, TTFT 1.812 ms (10 Laufe)unbekanntvLLM - 500,6 tok/s Generation, 4.007 tok/s Prefill, TTFT 3.936 ms (33 Laufe) | DIESER LAUF★ vLLM
★ vLLM 500,6 tok/s this runllama.cpp 479,6 tok/sunbekannt 21,2 tok/s

DRVby driver

6474853231620,02.2972.8653.4324.000Prefill (tok/s)Generation (tok/s)unbekannt - 500,6 tok/s Generation, 2.682 tok/s Prefill, TTFT 28.147 ms (91 Laufe)unbekanntAMD 7.0.0-27-generic - 21,2 tok/s Generation, 3.615 tok/s Prefill, TTFT 1.812 ms (10 Laufe)AMD 7.0.0-27-generic
unbekannt 500,6 tok/sAMD 7.0.0-27-generic 21,2 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× 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 2.84
Token / kWh105.45K
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)1.33B
☁️ 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-Coder-32B-Instruct2x AMD Radeon RX 7900 XTXQwen2.5-Coder-32B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen2.5-Coder-32B-InstructNVIDIA GeForce RTX 5090Qwen2.5-Coder-32B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition
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.