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

Qwen2.5-Coder-32B-Instruct

Performance benchmark · measured on 29.07.2026 04:27

Benchmark-IDrun-20260729-060802-af0697
Timebench 3 - Kombi (Prefill + Generation)Dense32BRuntime: llama.cppQuantisierung: Q4_K_M
Generation45,31tok/s
Prefill644,40tok/s
Time to First Token217.710,00ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
46of 76 systems

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

This run is better than 40 % of all comparable systems.
Generation 45,3 tok/s
-84 % vs Ø 275,8
Prefill 644,4 tok/s
-74 % vs Ø 2.440,1
Time to First Token 217.710 ms
+114 % vs Ø 101.921
Distribution in the field2 – 1.744 tok/s
Ø 276 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: NVIDIA GeForce RTX 5070 Ti · 16 GB VRAM
CPU: AMD Ryzen Threadripper PRO 5975WX 32-Cores
RAM: 247 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen2.5-Coder-32B-Instruct

Configuration

benchmark-konfiguration — run-20260729-060802-af0697
# LLM-Benchmark Konfiguration # Modell : Qwen2.5-Coder-32B-Instruct # Engine : llama.cpp # Run-ID : run-20260729-060802-af0697 # GPU : NVIDIA GeForce RTX 5070 Ti # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--bartowski--Qwen2.5-Coder-32B-Instruct-GGUF/snapshots/40b525506a4f98ed425882fa6dfc90cc8139065e/Qwen2.5-Coder-32B-Instruct-Q4_K_M.gguf \ --alias Qwen2.5-Coder-32B-Instruct \ --host 0.0.0.0 \ --port 8000 \ -ngl 30 \ -c 16384 \ -np 4 \ --jinja
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-Coder-32B-Instruct
Kontextlaenge?Maximale Anzahl Tokens (Eingabe + erzeugte Ausgabe zusammen), die das Modell pro Anfrage verarbeiten kann.16384
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird./home/godcore/.cache/huggingface/hub/models--bartowski--Qwen2.5-Coder-32B-Instruct-GGUF/snapshots/40b525506a4f98ed425882fa6dfc90cc8139065e/Qwen2.5-Coder-32B-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.30
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.16384
np4

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

6474853231620,001.8153.6295.444Prefill (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 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 ...AMD Radeon AI PRO R9700 - 21,2 tok/s Generation, 2.649 tok/s Prefill, TTFT 50.284 ms (27 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 45,3 tok/s Generation, 587 tok/s Prefill, TTFT 95.842 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
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/sAMD Radeon PRO W7900 Dual Slot 102,1 tok/sAMD Radeon PRO W7800 48GB 69,8 tok/s★ NVIDIA GeForce RTX 5070 Ti 45,3 tok/s this runAMD Radeon AI PRO R9700 21,2 tok/s

CPUby processor

6304733151580,01771.9043.6325.359Prefill (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 Threadripper PRO 5975WX 32-Cores - 102,1 tok/s Generation, 1.060 tok/s Prefill, TTFT 26.873 ms (18 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 5975WX 32-Cores 102,1 tok/s this run

MBby mainboard

6304733151580,01841.8973.6095.322Prefill (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. Pro WS WRX80E-SAGE SE WIFI - 102,1 tok/s Generation, 1.060 tok/s Prefill, TTFT 26.873 ms (18 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 102,1 tok/s this run

ENGby engine

6474853231620,01.3972.5203.6434.766Prefill (tok/s)Generation (tok/s)vLLM - 500,6 tok/s Generation, 4.138 tok/s Prefill, TTFT 3.727 ms (30 Laufe)vLLMunbekannt - 21,2 tok/s Generation, 3.615 tok/s Prefill, TTFT 1.812 ms (10 Laufe)unbekanntllama.cpp - 479,6 tok/s Generation, 2.025 tok/s Prefill, TTFT 39.839 ms (53 Laufe) | DIESER LAUF★ llama.cpp
vLLM 500,6 tok/s★ llama.cpp 479,6 tok/s this rununbekannt 21,2 tok/s

DRVby driver

6474853231620,02.4232.9423.4613.981Prefill (tok/s)Generation (tok/s)unbekannt - 500,6 tok/s Generation, 2.789 tok/s Prefill, TTFT 26.786 ms (83 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 (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 310 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)310 W estimated (TDP)GPU 300 + Board 10 W full load
Avg cost / hourEUR 0.093
Electricity / 1M tokensEUR 0.57
Token / kWh526.18K
Acquisition (system)EUR 5,000 partial priceGPU EUR 994 · CPU EUR 1,880 · RAM EUR 1,976 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 6,629
Output tokens (2 years)2.86B
☁️ 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-InstructNVIDIA GeForce RTX 5070 TiQwen2.5-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.