Created bymario-alka.dePowered bynoob2claw.detricoma.de
Contributed byMario AlkaQwen (Alibaba)

Qwen3-1.7B

Performance benchmark · measured on 22.09.2026 08:54

Benchmark-IDrun-20260922-071040-916c63
Timebench 3 - Kombi (Prefill + Generation)Dense1.7BRuntime: llama.cppQuantisierung: Q8_0
Generation156,39tok/s
Prefill9.841,62tok/s
Time to First Token248,00ms
Total duration13,59s
Concurrency1parallel
Ranking in the field
269of 1927 systems

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

This run is better than 86 % of all comparable systems.
Generation 156,4 tok/s
+102 % vs Ø 77,5
Prefill 9.841,6 tok/s
+246 % vs Ø 2.844,6
Time to First Token 248 ms
-99 % vs Ø 23.755
Distribution in the field0 – 471 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: AMD Radeon AI PRO R9700 · 32 GB VRAM
CPU: AMD Ryzen 3 3100 4-Core Processor
RAM: 31 GB
Mainboard: ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING

Setup

Runtime: llama.cpp
Quantization: Q8_0
Model: Qwen3-1.7B

Configuration

benchmark-konfiguration — run-20260922-071040-916c63
# LLM-Benchmark Konfiguration # Modell : Qwen3-1.7B # Engine : llama.cpp # Run-ID : run-20260922-071040-916c63 # GPU : AMD Radeon AI PRO R9700 # CPU : AMD Ryzen 3 3100 4-Core Processor # RAM : 31 GB bench@llm-benchmark:~$ llama-server \ -m /home/godcore/models/Qwen3-1.7B-Q8_0.gguf \ --alias Qwen3-1.7B \ -ngl 999 \ -fa on \ -c 49152 \ -np 12 '(AMD' Radeon AI PRO R9700, ROCm 7.2.4, 'HIP_VISIBLE_DEVICES=0)'
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.Qwen3-1.7B
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/Qwen3-1.7B-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

Qwen3-1.7B 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

6204653101550,006.70613.41120.117Prefill (tok/s)Generation (tok/s)AMD Radeon RX 7900 XTX - 445,2 tok/s Generation, 16.451 tok/s Prefill, TTFT 968 ms (9 Laufe)AMD Radeon RX 7900 XTXAMD Oberon (PlayStation 5) - 202,4 tok/s Generation, 1.591 tok/s Prefill, TTFT 4.381 ms (2 Laufe)AMD Oberon (PlayStati...CPU-only - 100,5 tok/s Generation, 1.572 tok/s Prefill, TTFT 143.877 ms (5 Laufe)CPU-onlyAMD Radeon AI PRO R9700 - 492,7 tok/s Generation, 14.046 tok/s Prefill, TTFT 873 ms (3 Laufe) | DIESER LAUF★ AMD Radeon AI PRO R97...
★ AMD Radeon AI PRO R9700 492,7 tok/s this runAMD Radeon RX 7900 XTX 445,2 tok/sAMD Oberon (PlayStation 5) 202,4 tok/sCPU-only 100,5 tok/s

CPUby processor

6404803201600,007.76015.52123.281Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 3955WX 16-Cores - 445,2 tok/s Generation, 18.781 tok/s Prefill, TTFT 935 ms (6 Laufe)AMD Ryzen Threadrippe...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 437,4 tok/s Generation, 11.792 tok/s Prefill, TTFT 1.033 ms (3 Laufe)Intel(R) Xeon(R) CPU ...AMD Zen2 8-Core (PlayStation 5) - 202,4 tok/s Generation, 1.591 tok/s Prefill, TTFT 4.381 ms (2 Laufe)AMD Zen2 8-Core (Play...Apple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) - 100,5 tok/s Generation, 4.497 tok/s Prefill, TTFT 604 ms (1 Lauf)Apple M6 (unified CPU...Apple M6 (unified CPU/GPU SoC) - 85,5 tok/s Generation, 3.232 tok/s Prefill, TTFT 815 ms (1 Lauf)Apple M6 (unified CPU...4 x Cortex-A78C + 4 x Cortex-A55 - 4,0 tok/s Generation, 43 tok/s Prefill, TTFT 239.322 ms (3 Laufe)4 x Cortex-A78C + 4 x...AMD Ryzen 3 3100 4-Core Processor - 492,7 tok/s Generation, 14.046 tok/s Prefill, TTFT 873 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 3 3100 4-Co...
★ AMD Ryzen 3 3100 4-Core Processor 492,7 tok/s this runAMD Ryzen Threadripper PRO 3955WX 16-Cores 445,2 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 437,4 tok/sAMD Zen2 8-Core (PlayStation 5) 202,4 tok/sApple M6 (unified CPU/GPU SoC, ARM64, AdvSIMD) 100,5 tok/sApple M6 (unified CPU/GPU SoC) 85,5 tok/s4 x Cortex-A78C + 4 x Cortex-A55 4,0 tok/s

MBby mainboard

6204653101550,007.72315.44623.170Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 445,2 tok/s Generation, 18.781 tok/s Prefill, TTFT 935 ms (6 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 437,4 tok/s Generation, 11.792 tok/s Prefill, TTFT 1.033 ms (3 Laufe)Dell Inc. PowerEdge R...unbekannt - 202,4 tok/s Generation, 662 tok/s Prefill, TTFT 145.346 ms (5 Laufe)unbekanntApple Mac mini - 100,5 tok/s Generation, 3.865 tok/s Prefill, TTFT 710 ms (2 Laufe)Apple Mac miniASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 492,7 tok/s Generation, 14.046 tok/s Prefill, TTFT 873 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 492,7 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 445,2 tok/sDell Inc. PowerEdge R820 437,4 tok/sunbekannt 202,4 tok/sApple Mac mini 100,5 tok/s

ENGby engine

6234683121560,009.42718.85428.281Prefill (tok/s)Generation (tok/s)vLLM - 387,7 tok/s Generation, 23.277 tok/s Prefill, TTFT 1.026 ms (3 Laufe)vLLMlmstudio-mlx - 100,5 tok/s Generation, 4.497 tok/s Prefill, TTFT 604 ms (1 Lauf)lmstudio-mlxOllama - 85,5 tok/s Generation, 3.232 tok/s Prefill, TTFT 815 ms (1 Lauf)Ollamallama.cpp - 492,7 tok/s Generation, 8.834 tok/s Prefill, TTFT 52.499 ms (14 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 492,7 tok/s this runvLLM 387,7 tok/slmstudio-mlx 100,5 tok/sOllama 85,5 tok/s

DRVby driver

5425174934684439.95610.38010.80311.227Prefill (tok/s)Generation (tok/s)unbekannt - 492,7 tok/s Generation, 10.592 tok/s Prefill, TTFT 38.920 ms (19 Laufe)unbekannt
unbekannt 492,7 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 20 W
⚡ TDP 300 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)300 W estimated (TDP)GPU 300 W full load
Avg cost / hourEUR 0.090
Electricity / 1M tokensEUR 0.16
Token / kWh1.88M
Acquisition (system)EUR 1,520 partial priceGPU EUR 1,400 · PSU EUR 120
Electricity (2 years)–
TCO (2 years)EUR 3,097
Output tokens (2 years)9.86B
☁️ 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 (20 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

Qwen3-1.7BAMD Radeon AI PRO R9700Qwen3-1.7BAMD Oberon (PlayStation 5)Qwen3-1.7B2x AMD Radeon RX 7900 XTXQwen3-1.7B2x 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.