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

Qwen3-0.6B

Performance benchmark · measured on 07.10.2026 22:34

Benchmark-IDrun-20261007-210611-524f33
Timebench 3 - Kombi (Prefill + Generation)Dense0.6BRuntime: llama.cppQuantisierung: Q4_K_M
ℹ
Public note: Arduino Q (ventunoq) . ARM RK3588 8-Core (4x Cortex-A78C + 4x Cortex-A55) . 14 GB RAM . llama.cpp CPU (Edge-Geraet)
Generation8,04tok/s
Prefill107,71tok/s
Time to First Token227.805,00ms
Total duration1.200,00s
Concurrency10parallel
Ranking in the field
6of 20 systems

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

This run is better than 74 % of all comparable systems.
Generation 8,0 tok/s
-11 % vs Ø 9,0
Prefill 107,7 tok/s
+12 % vs Ø 95,9
Time to First Token 227.805 ms
-4 % vs Ø 236.526
Distribution in the field0 – 71 tok/s
Ø 9 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: Keine GPU (CPU-only)
CPU: 4 x Cortex-A78C + 4 x Cortex-A55
RAM: 15 GB

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3-0.6B

Configuration

benchmark-konfiguration — run-20261007-210611-524f33
# LLM-Benchmark Konfiguration # Modell : Qwen3-0.6B # Engine : llama.cpp # Run-ID : run-20261007-210611-524f33 # GPU : Keine GPU (CPU-only) # CPU : 4 x Cortex-A78C + 4 x Cortex-A55 # RAM : 15 GB bench@llm-benchmark:~$ llama-server \ -m Qwen3-0.6B-Q4_K_M.gguf \ --alias Qwen3-0.6B \ -ngl 0 \ -t 8 \ -c 40960 \ -np 10 '(ARM' RK3588 'CPU)'
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.40960
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.Qwen3-0.6B-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.0
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).8
Kontext?Groesse des Kontextfensters in Token. 0 = der beim Training verwendete Kontext des Modells.40960
np10
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

7285463641820,0029.58059.16088.740Prefill (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...NVIDIA GeForce RTX 4090 - 503,3 tok/s Generation, 71.575 tok/s Prefill, TTFT 174 ms (3 Laufe)NVIDIA GeForce RTX 40...AMD Radeon RX 7900 XTX - 495,5 tok/s Generation, 22.637 tok/s Prefill, TTFT 718 ms (8 Laufe)AMD Radeon RX 7900 XTXAMD 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, 74 tok/s Prefill, TTFT 126.155 ms (4 Laufe) | DIESER LAUF★ CPU-only
AMD Radeon AI PRO R9700 561,4 tok/sNVIDIA GeForce RTX 4090 503,3 tok/sAMD Radeon RX 7900 XTX 495,5 tok/sAMD Oberon (PlayStation 5) 302,6 tok/s★ CPU-only 8,0 tok/s this run

CPUby processor

7295473651820,0019.12238.24457.366Prefill (tok/s)Generation (tok/s)AMD Ryzen 3 3100 4-Core Processor - 561,4 tok/s Generation, 46.266 tok/s Prefill, TTFT 374 ms (6 Laufe)AMD Ryzen 3 3100 4-Co...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 495,5 tok/s Generation, 27.231 tok/s Prefill, TTFT 657 ms (5 Laufe)AMD Ryzen Threadrippe...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...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...4 x Cortex-A78C + 4 x Cortex-A55 - 8,0 tok/s Generation, 90 tok/s Prefill, TTFT 132.604 ms (3 Laufe) | DIESER LAUF★ 4 x Cortex-A78C + 4 x...
AMD Ryzen 3 3100 4-Core Processor 561,4 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 495,5 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 480,5 tok/sAMD Zen2 8-Core (PlayStation 5) 302,6 tok/s★ 4 x Cortex-A78C + 4 x Cortex-A55 8,0 tok/s this runAMD Jaguar 8-Core (PlayStation 4) 3,8 tok/s

MBby mainboard

669551432313195029.52259.04488.565Prefill (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....Micro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) - 503,3 tok/s Generation, 71.575 tok/s Prefill, TTFT 174 ms (3 Laufe)Micro-Star Internatio...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 495,5 tok/s Generation, 27.231 tok/s Prefill, TTFT 657 ms (5 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)unbekannt
ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 561,4 tok/sMicro-Star International Co., Ltd. B550M PRO-VDH WIFI (MS-7C95) 503,3 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 495,5 tok/sDell Inc. PowerEdge R820 480,5 tok/sunbekannt 302,6 tok/s

ENGby engine

629581532484436021.26142.52263.782Prefill (tok/s)Generation (tok/s)vLLM - 503,3 tok/s Generation, 52.963 tok/s Prefill, TTFT 499 ms (6 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 503,3 tok/s

DRVby driver

61859056153350521.85322.78323.71324.643Prefill (tok/s)Generation (tok/s)unbekannt - 561,4 tok/s Generation, 23.248 tok/s Prefill, TTFT 25.860 ms (20 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 (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 %
🔌 Idle 0 W
⚡ TDP 10 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)0 W missing
Avg cost / hour–
Electricity / 1M tokens–
Token / kWh–
Acquisition (system)– partial price
Electricity (2 years)–
TCO (2 years)–
Output tokens (2 years)507.10M
☁️ External LLM (API) – comparison
External LLM cost (2 years)–
Savings vs. external (2 years)–
No power draw measured – values estimated from GPU TDP + CPU (idle + 15 %) + board.

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 (0 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

Qwen3-0.6BKeine GPU (CPU-only)Qwen3-0.6BAMD Radeon AI PRO R9700Qwen3-0.6BNVIDIA GeForce RTX 4090Qwen3-0.6B2x 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.