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

Qwen3.6-35B-A3B

Performance benchmark · measured on 29.07.2026 08:54

Benchmark-IDrun-20260729-105337-620afe
Timebench 3 - Kombi (Prefill + Generation)MoE35BRuntime: llama.cppQuantisierung: UD-Q4_K_M
Generation851,97tok/s
Prefill3.889,65tok/s
Time to First Token14.433,00ms
Total duration80,58s
Concurrency10parallel
Ranking in the field
22of 53 systems

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

This run is better than 60 % of all comparable systems.
Generation 852,0 tok/s
+45 % vs Ø 585,7
Prefill 3.889,7 tok/s
-22 % vs Ø 5.008,2
Time to First Token 14.433 ms
-70 % vs Ø 48.089
Distribution in the field4 – 1.493 tok/s
Ø 586 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 3090 Ti · 24 GB VRAM
CPU: AMD Ryzen 9 8945HX with Radeon Graphics
RAM: 92 GB
Mainboard: Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series)

Setup

Runtime: llama.cpp
Quantization: UD-Q4_K_M
Model: Qwen3.6-35B-A3B

Configuration

benchmark-konfiguration — run-20260729-105337-620afe
# LLM-Benchmark Konfiguration # Modell : Qwen3.6-35B-A3B # Engine : llama.cpp # Run-ID : run-20260729-105337-620afe # GPU : NVIDIA GeForce RTX 3090 Ti # CPU : AMD Ryzen 9 8945HX with Radeon Graphics # RAM : 92 GB bench@llm-benchmark:~$ /root/llama.cpp/build/bin/llama-server \ -m /root/.cache/huggingface/hub/models--unsloth--Qwen3.6-35B-A3B-GGUF/snapshots/a483e9e6cbd595906af30beda3187c2663a1118c/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf \ --alias Qwen3.6-35B-A3B \ --host 0.0.0.0 \ --port 8000 \ -ngl 999 \ -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.Qwen3.6-35B-A3B
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./root/.cache/huggingface/hub/models--unsloth--Qwen3.6-35B-A3B-GGUF/snapshots/a483e9e6cbd595906af30beda3187c2663a1118c/Qwen3.6-35B-A3B-UD-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.999
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

Qwen3.6-35B-A3B 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

1.9351.4519674840,005.20710.41415.621Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.489,1 tok/s Generation, 12.607 tok/s Prefill, TTFT 2.168 ms (6 Laufe)NVIDIA RTX PRO 6000 B...AMD Radeon AI PRO R9700 - 206,9 tok/s Generation, 3.263 tok/s Prefill, TTFT 3.552 ms (3 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 142,9 tok/s Generation, 499 tok/s Prefill, TTFT 32.007 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon 8060S Graphics - 103,2 tok/s Generation, 1.206 tok/s Prefill, TTFT 8.616 ms (3 Laufe)AMD Radeon 8060S Grap...CPU-only - 4,3 tok/s Generation, 62 tok/s Prefill, TTFT 31.435 ms (1 Lauf)CPU-onlyNVIDIA GeForce RTX 3090 Ti - 852,0 tok/s Generation, 3.431 tok/s Prefill, TTFT 6.717 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 30...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.489,1 tok/s★ NVIDIA GeForce RTX 3090 Ti 852,0 tok/s this runAMD Radeon AI PRO R9700 206,9 tok/sNVIDIA GeForce RTX 5070 Ti 142,9 tok/sAMD Radeon 8060S Graphics 103,2 tok/sCPU-only 4,3 tok/s

CPUby processor

1.9351.4519674840,005.20710.41415.621Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 1.489,1 tok/s Generation, 12.607 tok/s Prefill, TTFT 2.168 ms (6 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 206,9 tok/s Generation, 3.263 tok/s Prefill, TTFT 3.552 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 142,9 tok/s Generation, 499 tok/s Prefill, TTFT 32.007 ms (6 Laufe)AMD Ryzen Threadrippe...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 103,2 tok/s Generation, 1.206 tok/s Prefill, TTFT 8.616 ms (3 Laufe)AMD RYZEN AI MAX+ 395...Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz - 4,3 tok/s Generation, 62 tok/s Prefill, TTFT 31.435 ms (1 Lauf)Intel(R) Xeon(R) CPU ...AMD Ryzen 9 8945HX with Radeon Graphics - 852,0 tok/s Generation, 3.431 tok/s Prefill, TTFT 6.717 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen 9 8945HX wi...
AMD Ryzen 9 9950X 16-Core Processor 1.489,1 tok/s★ AMD Ryzen 9 8945HX with Radeon Graphics 852,0 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 206,9 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 142,9 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 103,2 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 4,3 tok/s

MBby mainboard

1.9351.4519674840,005.20710.41415.621Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.489,1 tok/s Generation, 12.607 tok/s Prefill, TTFT 2.168 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 206,9 tok/s Generation, 3.263 tok/s Prefill, TTFT 3.552 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 142,9 tok/s Generation, 499 tok/s Prefill, TTFT 32.007 ms (6 Laufe)ASUSTeK COMPUTER INC....Bosgame AXB35-02 (BeyondMax Series) - 103,2 tok/s Generation, 1.206 tok/s Prefill, TTFT 8.616 ms (3 Laufe)Bosgame AXB35-02 (Bey...Dell Inc. PowerEdge R820 - 4,3 tok/s Generation, 62 tok/s Prefill, TTFT 31.435 ms (1 Lauf)Dell Inc. PowerEdge R...Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 852,0 tok/s Generation, 3.431 tok/s Prefill, TTFT 6.717 ms (3 Laufe) | DIESER LAUF★ Meigao Innovation Tec...
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.489,1 tok/s★ Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 852,0 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 206,9 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 142,9 tok/sBosgame AXB35-02 (BeyondMax Series) 103,2 tok/sDell Inc. PowerEdge R820 4,3 tok/s

ENGby engine

1.7451.4831.2219596971.2484.2227.19610.170Prefill (tok/s)Generation (tok/s)vLLM - 952,8 tok/s Generation, 8.609 tok/s Prefill, TTFT 9.202 ms (7 Laufe)vLLMllama.cpp - 1.489,1 tok/s Generation, 2.809 tok/s Prefill, TTFT 15.248 ms (15 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.489,1 tok/s this runvLLM 952,8 tok/s

DRVby driver

1.6381.5641.4891.4151.3404.3754.5614.7474.934Prefill (tok/s)Generation (tok/s)unbekannt - 1.489,1 tok/s Generation, 4.654 tok/s Prefill, TTFT 13.324 ms (22 Laufe)unbekannt
unbekannt 1.489,1 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 50 W
⚡ TDP 477 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)477 W estimated (TDP)GPU 450 + CPU 17 + Board 10 W full load
Avg cost / hourEUR 0.14
Electricity / 1M tokensEUR 0.047
Token / kWh6.43M
Acquisition (system)EUR 2,986 partial priceGPU EUR 999 · CPU EUR 549 · RAM EUR 1,288 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 5,494
Output tokens (2 years)53.74B
☁️ 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 (50 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

Qwen3.6-35B-A3BNVIDIA GeForce RTX 3090 TiQwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.6-35B-A3B3x AMD Radeon AI PRO R9700
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.