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

Qwen3-0.6B

Performance benchmark · measured on 22.09.2026 11:33

Benchmark-IDrun-20260922-095735-570c64
Timebench 3 - Kombi (Prefill + Generation)Dense0.6BRuntime: llama.cppQuantisierung: Q8_0
Generation495,51tok/s
Prefill19.609,49tok/s
Time to First Token627,50ms
Total duration22,92s
Concurrency5parallel
Ranking in the field
1of 116 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 5× concurrent

This run is better than 100 % of all comparable systems.
Generation 495,5 tok/s
+199 % vs Ø 165,5
Prefill 19.609,5 tok/s
+206 % vs Ø 6.410,5
Time to First Token 628 ms
-96 % vs Ø 17.665
Distribution in the field2 – 496 tok/s
Ø 165 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 5× concurrent · Generation (tok/s)

Hardware

GPU: 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: llama.cpp
Quantization: Q8_0
Model: Qwen3-0.6B

Configuration

benchmark-konfiguration — run-20260922-095735-570c64
# LLM-Benchmark Konfiguration # Modell : Qwen3-0.6B # Engine : llama.cpp # Run-ID : run-20260922-095735-570c64 # GPU : AMD Radeon RX 7900 XTX # CPU : AMD Ryzen Threadripper PRO 3955WX 16-Cores # RAM : 63 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/models/Qwen3-0.6B-Q8_0.gguf \ --alias Qwen3-0.6B \ -ngl 999 \ -fa on \ -c 49152 \ -np 12 '(AMD' Radeon RX 7900 XTX, ROCm '7.2.4)'
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.Qwen3-0.6B
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/Qwen3-0.6B-Q8_0.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
execution_typelocal

All benchmarks of this model To leaderboard

Anzeige
Model comparison

Qwen3-0.6B 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

7295473651820,009.35518.71128.066Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 561,4 tok/s Generation, 20.958 tok/s Prefill, TTFT 573 ms (3 Laufe)AMD Radeon AI PRO R97...AMD Oberon (PlayStation 5) - 302,6 tok/s Generation, 2.983 tok/s Prefill, TTFT 2.304 ms (2 Laufe)AMD Oberon (PlayStati...CPU-only - 8,0 tok/s Generation, 90 tok/s Prefill, TTFT 132.604 ms (3 Laufe)CPU-onlyAMD Liverpool (PlayStation 4) - 3,8 tok/s Generation, 23 tok/s Prefill, TTFT 106.805 ms (1 Lauf)AMD Liverpool (PlaySt...AMD Radeon RX 7900 XTX - 495,5 tok/s Generation, 22.637 tok/s Prefill, TTFT 718 ms (8 Laufe) | DIESER LAUF★ AMD Radeon RX 7900 XTX
AMD Radeon AI PRO R9700 561,4 tok/s★ AMD Radeon RX 7900 XTX 495,5 tok/s this runAMD Oberon (PlayStation 5) 302,6 tok/sCPU-only 8,0 tok/sAMD Liverpool (PlayStation 4) 3,8 tok/s

CPUby processor

7295473651820,0011.25422.50833.763Prefill (tok/s)Generation (tok/s)AMD Ryzen 3 3100 4-Core Processor - 561,4 tok/s Generation, 20.958 tok/s Prefill, TTFT 573 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 480,5 tok/s Generation, 14.980 tok/s Prefill, TTFT 819 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Zen2 8-Core (PlayStation 5) - 302,6 tok/s Generation, 2.983 tok/s Prefill, TTFT 2.304 ms (2 Laufe)AMD Zen2 8-Core (Play...4 x Cortex-A78C + 4 x Cortex-A55 - 8,0 tok/s Generation, 90 tok/s Prefill, TTFT 132.604 ms (3 Laufe)4 x Cortex-A78C + 4 x...AMD Jaguar 8-Core (PlayStation 4) - 3,8 tok/s Generation, 23 tok/s Prefill, TTFT 106.805 ms (1 Lauf)AMD Jaguar 8-Core (Pl...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 495,5 tok/s Generation, 27.231 tok/s Prefill, TTFT 657 ms (5 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 3 3100 4-Core Processor 561,4 tok/s★ AMD Ryzen Threadripper PRO 3955WX 16-Cores 495,5 tok/s this runIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 480,5 tok/sAMD Zen2 8-Core (PlayStation 5) 302,6 tok/s4 x Cortex-A78C + 4 x Cortex-A55 8,0 tok/sAMD Jaguar 8-Core (PlayStation 4) 3,8 tok/s

MBby mainboard

669551432313195011.19322.38633.579Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 561,4 tok/s Generation, 20.958 tok/s Prefill, TTFT 573 ms (3 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 480,5 tok/s Generation, 14.980 tok/s Prefill, TTFT 819 ms (3 Laufe)Dell Inc. PowerEdge R...unbekannt - 302,6 tok/s Generation, 1.043 tok/s Prefill, TTFT 84.871 ms (6 Laufe)unbekanntASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 495,5 tok/s Generation, 27.231 tok/s Prefill, TTFT 657 ms (5 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 561,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 495,5 tok/s this runDell Inc. PowerEdge R820 480,5 tok/sunbekannt 302,6 tok/s

ENGby engine

6535634733832934.16016.34228.52340.704Prefill (tok/s)Generation (tok/s)vLLM - 384,2 tok/s Generation, 34.352 tok/s Prefill, TTFT 825 ms (3 Laufe)vLLMllama.cpp - 561,4 tok/s Generation, 10.512 tok/s Prefill, TTFT 36.729 ms (14 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 561,4 tok/s this runvLLM 384,2 tok/s

DRVby driver

61859056153350513.83614.42515.01415.603Prefill (tok/s)Generation (tok/s)unbekannt - 561,4 tok/s Generation, 14.719 tok/s Prefill, TTFT 30.393 ms (17 Laufe)unbekannt
unbekannt 561,4 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (5× 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 365 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)365 W estimated (TDP)GPU 355 + Board 10 W full load
Avg cost / hourEUR 0.11
Electricity / 1M tokensEUR 0.061
Token / kWh4.89M
Acquisition (system)EUR 1,703 partial priceGPU EUR 1,049 · RAM EUR 504 · PSU EUR 150
Electricity (2 years)–
TCO (2 years)EUR 3,621
Output tokens (2 years)31.25B
☁️ 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

Qwen3-0.6BAMD Radeon RX 7900 XTXQwen3-0.6BAMD Radeon AI PRO R9700Qwen3-0.6BAMD Oberon (PlayStation 5)Qwen3-0.6B2x AMD Radeon RX 7900 XTX
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.