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

Qwen3.5-35B-A3B

Performance benchmark · measured on 29.07.2026 01:38

Benchmark-IDrun-20260729-032128-74fd1d
Timebench 3 - Kombi (Prefill + Generation)MoE35BRuntime: llama.cppQuantisierung: Q4_K_M
Generation829,61tok/s
Prefill7.024,83tok/s
Time to First Token2.629,00ms
Total duration24,86s
Concurrency5parallel
Ranking in the field
20of 64 systems

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

This run is better than 70 % of all comparable systems.
Generation 829,6 tok/s
+46 % vs Ø 566,5
Prefill 7.024,8 tok/s
-24 % vs Ø 9.241,9
Time to First Token 2.629 ms
-81 % vs Ø 13.746
Distribution in the field0 – 1.349 tok/s
Ø 567 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

gemma-4-E2B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181606-0adf6d
1.349,3 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9
1.136,3 tok/s
NVIDIA-Nemotron-3-Nano-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032121-305ad6
1.007,8 tok/s
Nemotron-Cascade-2-30B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032120-4b8514
1.007,3 tok/s
Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032119-1ddf01
1.007,0 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-17e7b6
975,1 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-d94e39
967,9 tok/s
Laguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-8dd350
966,1 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032124-ebc781
938,2 tok/s
Mamba-Codestral-7B-v0.1NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-194136-f3211a
927,1 tok/s
Qwen3-30B-A3B-Thinking-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032123-277335
926,2 tok/s
gemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bf4219
914,3 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032122-601ed1
910,8 tok/s
Qwen3.5-35B-A3B this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260729-032128-74fd1d
829,6 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA RTX PRO 6000 Blackwell Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen 9 9950X 16-Core Processor
RAM: 92 GB
Mainboard: ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3.5-35B-A3B

Configuration

benchmark-konfiguration — run-20260729-032128-74fd1d
# LLM-Benchmark Konfiguration # Modell : Qwen3.5-35B-A3B # Engine : llama.cpp # Run-ID : run-20260729-032128-74fd1d # GPU : NVIDIA RTX PRO 6000 Blackwell Workstation Edition # CPU : AMD Ryzen 9 9950X 16-Core Processor # RAM : 92 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--unsloth--Qwen3.5-35B-A3B-GGUF/snapshots/bc014a17be43adabd7066b7a86075ff935c6a4e2/Qwen3.5-35B-A3B-Q4_K_M.gguf \ --alias Qwen3.5-35B-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.Qwen3.5-35B-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./home/godcore/.cache/huggingface/hub/models--unsloth--Qwen3.5-35B-A3B-GGUF/snapshots/bc014a17be43adabd7066b7a86075ff935c6a4e2/Qwen3.5-35B-A3B-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

Qwen3.5-35B-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

1.9551.4669774890,005.26410.52815.792Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 205,4 tok/s Generation, 2.994 tok/s Prefill, TTFT 2.915 ms (4 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 142,2 tok/s Generation, 508 tok/s Prefill, TTFT 31.910 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon 8060S Graphics - 109,7 tok/s Generation, 1.204 tok/s Prefill, TTFT 8.627 ms (3 Laufe)AMD Radeon 8060S Grap...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.520,4 tok/s Generation, 12.809 tok/s Prefill, TTFT 2.176 ms (6 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.520,4 tok/s this runAMD Radeon AI PRO R9700 205,4 tok/sNVIDIA GeForce RTX 5070 Ti 142,2 tok/sAMD Radeon 8060S Graphics 109,7 tok/s

CPUby processor

1.9551.4669774890,005.26410.52815.792Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 205,4 tok/s Generation, 2.994 tok/s Prefill, TTFT 2.915 ms (4 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 142,2 tok/s Generation, 508 tok/s Prefill, TTFT 31.910 ms (6 Laufe)AMD Ryzen Threadrippe...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 109,7 tok/s Generation, 1.204 tok/s Prefill, TTFT 8.627 ms (3 Laufe)AMD RYZEN AI MAX+ 395...AMD Ryzen 9 9950X 16-Core Processor - 1.520,4 tok/s Generation, 12.809 tok/s Prefill, TTFT 2.176 ms (6 Laufe) | DIESER LAUF★ AMD Ryzen 9 9950X 16-...
★ AMD Ryzen 9 9950X 16-Core Processor 1.520,4 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 205,4 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 142,2 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 109,7 tok/s

MBby mainboard

1.9551.4669774890,005.26410.52815.792Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 205,4 tok/s Generation, 2.994 tok/s Prefill, TTFT 2.915 ms (4 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 142,2 tok/s Generation, 508 tok/s Prefill, TTFT 31.910 ms (6 Laufe)ASUSTeK COMPUTER INC....Bosgame AXB35-02 (BeyondMax Series) - 109,7 tok/s Generation, 1.204 tok/s Prefill, TTFT 8.627 ms (3 Laufe)Bosgame AXB35-02 (Bey...ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.520,4 tok/s Generation, 12.809 tok/s Prefill, TTFT 2.176 ms (6 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.520,4 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 205,4 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 142,2 tok/sBosgame AXB35-02 (BeyondMax Series) 109,7 tok/s

ENGby engine

1.7711.5231.2741.0267781.4424.1036.7649.425Prefill (tok/s)Generation (tok/s)vLLM - 1.028,6 tok/s Generation, 8.015 tok/s Prefill, TTFT 8.201 ms (8 Laufe)vLLMllama.cpp - 1.520,4 tok/s Generation, 2.852 tok/s Prefill, TTFT 16.041 ms (11 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.520,4 tok/s this runvLLM 1.028,6 tok/s

DRVby driver

1.6721.5961.5201.4441.3684.7244.9255.1265.327Prefill (tok/s)Generation (tok/s)unbekannt - 1.520,4 tok/s Generation, 5.026 tok/s Prefill, TTFT 12.740 ms (19 Laufe)unbekannt
unbekannt 1.520,4 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 70 W
⚡ TDP 644 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)644 W estimated (TDP)GPU 600 + CPU 29 + Board 15 W full load
Avg cost / hourEUR 0.19
Electricity / 1M tokensEUR 0.065
Token / kWh4.64M
Acquisition (system)EUR 15,248 full priceGPU EUR 13,000 · CPU EUR 649 · Board EUR 499 · RAM EUR 920 · PSU EUR 180
Electricity (2 years)
TCO (2 years)EUR 18,632
Output tokens (2 years)52.33B
☁️ 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 (70 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

Qwen3.5-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.5-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.5-35B-A3B3x AMD Radeon AI PRO R9700Qwen3.5-35B-A3BAMD Radeon 8060S Graphics
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.