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

Qwen3.6-35B-A3B

Performance benchmark · measured on 24.10.2026 16:49

Benchmark-IDrun-20261024-151250-ef9d1b
Timebench 3 - Kombi (Prefill + Generation)MoE35BRuntime: llama.cppQuantisierung: Q4_K_M
Generation124,89tok/s
Prefill2.476,42tok/s
Time to First Token6.821,00ms
Total duration165,90s
Concurrency5parallel
Ranking in the field
1of 5 systems

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

This run is better than 100 % of all comparable systems.
Generation 124,9 tok/s
+21 % vs Ø 103,5
Prefill 2.476,4 tok/s
0 % vs Ø 2.481,7
Time to First Token 6.821 ms
-14 % vs Ø 7.933
Distribution in the field72 – 125 tok/s
Ø 103 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: NVIDIA RTX SPARK (N1X)
CPU: NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU)
RAM: 128 GB
Mainboard: ASUS H7607BA

Setup

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

Configuration

benchmark-konfiguration — run-20261024-151250-ef9d1b
# LLM-Benchmark Konfiguration # Modell : Qwen3.6-35B-A3B # Engine : llama.cpp # Run-ID : run-20261024-151250-ef9d1b # GPU : NVIDIA RTX SPARK (N1X) # CPU : NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) # RAM : 128 GB bench@llm-benchmark:~$ 'C:\Users\mail\.lmstudio\extensions\backends\llama.cpp-win-arm64-nvidia-cuda13-2.61.0\llama-server.exe' \ --model 'C:\Users\mail\Documents\Codex\2026-10-24\mach\work\models\Qwen3.6-35B-A3B-Q4_K_M.gguf' \ --alias benchmark-local \ --host 127.0.0.1 \ --port 18765 \ --device CUDA0 \ --gpu-layers all \ --parallel 10 \ --kv-unified \ --kv-unified-per-slot 4096 \ --cache-type-k q8_0 \ --cache-type-v q8_0 \ --threads 20 \ --threads-batch 20 \ --batch-size 1024 \ --ubatch-size 256 \ --flash-attn on \ --fit off \ --no-cache-prompt \ --no-cache-idle-slots \ --cache-ram 0 \ --spec-type none \ --metrics \ --slots
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.4096
Batch-Groesse?Logische Batchgroesse fuer die Prompt-Verarbeitung (Anzahl Token pro Prefill-Durchlauf).1024
cache-ram0
K-Cache-Typ?Datentyp des K-Anteils im KV-Cache (f16/q8_0/q4_0 ...). Quantisiert senkt den VRAM-Bedarf bei leichtem Qualitaetsverlust.q8_0
V-Cache-Typ?Datentyp des V-Anteils im KV-Cache (f16/q8_0/q4_0 ...). Quantisierung braucht meist aktiviertes flash-attn.q8_0
deviceCUDA0
fitoff
Flash Attention?FlashAttention fuer schnellere und speichersparende Attention. Wert on/off/auto je nach Build.on
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.all
kv-unifiedaktiv
kv-unified-per-slot4096
metricsaktiv
Modellpfad?Pfad zur GGUF-Modelldatei, die geladen und ausgeliefert wird.C:\Users\mail\Documents\Codex\2026-10-24\mach\work\models\Qwen3.6-35B-A3B-Q4_K_M.gguf
no-cache-idle-slotsaktiv
no-cache-promptaktiv
Parallel?Anzahl paralleler Slots/Sequenzen, die der Server gleichzeitig bedient. Der Kontext wird auf die Slots aufgeteilt.10
slotsaktiv
spec-typenone
Threads?Anzahl CPU-Threads fuer die Token-Generierung (Decode).20
Batch-Threads?Anzahl CPU-Threads fuer Prompt-Verarbeitung und Batch (Prefill).20
Micro-Batch?Physische Micro-Batchgroesse. Begrenzt, wie viele Token gleichzeitig durch die Compute-Pipeline laufen.256
execution_typelocal

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

1.9481.4619744870,004.6859.37014.055Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.499,4 tok/s Generation, 11.344 tok/s Prefill, TTFT 2.939 ms (8 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 5090 - 1.409,4 tok/s Generation, 4.912 tok/s Prefill, TTFT 4.113 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.367,3 tok/s Generation, 6.432 tok/s Prefill, TTFT 4.005 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 852,0 tok/s Generation, 3.423 tok/s Prefill, TTFT 7.930 ms (9 Laufe)NVIDIA GeForce RTX 30...NVIDIA RTX A6000 - 800,4 tok/s Generation, 11.326 tok/s Prefill, TTFT 2.649 ms (30 Laufe)NVIDIA RTX A6000AMD Radeon RX 7900 XTX - 450,5 tok/s Generation, 3.150 tok/s Prefill, TTFT 4.777 ms (6 Laufe)AMD Radeon RX 7900 XTXNVIDIA GeForce RTX 3090 - 341,5 tok/s Generation, 3.647 tok/s Prefill, TTFT 2.792 ms (3 Laufe)NVIDIA GeForce RTX 30...AMD Radeon PRO W7900 Dual Slot - 296,2 tok/s Generation, 3.120 tok/s Prefill, TTFT 4.797 ms (18 Laufe)AMD Radeon PRO W7900 ...AMD Radeon AI PRO R9700 - 271,4 tok/s Generation, 3.037 tok/s Prefill, TTFT 20.347 ms (35 Laufe)AMD Radeon AI PRO R97...AMD Radeon PRO W7800 48GB - 235,5 tok/s Generation, 4.679 tok/s Prefill, TTFT 3.874 ms (9 Laufe)AMD Radeon PRO W7800 ...NVIDIA Tesla V100 PCIe 32GB - 225,9 tok/s Generation, 975 tok/s Prefill, TTFT 8.633 ms (3 Laufe)NVIDIA Tesla V100 PCI...NVIDIA DGX SPARK (GB10) - 169,4 tok/s Generation, 3.685 tok/s Prefill, TTFT 2.454 ms (11 Laufe)NVIDIA DGX SPARK (GB1...NVIDIA GeForce RTX 5070 Ti - 142,9 tok/s Generation, 499 tok/s Prefill, TTFT 32.007 ms (6 Laufe)NVIDIA GeForce RTX 50...Intel Arc Pro B70 - 124,5 tok/s Generation, 578 tok/s Prefill, TTFT 5.272 ms (7 Laufe)Intel Arc Pro B70AMD Radeon 8060S Graphics - 98,3 tok/s Generation, 863 tok/s Prefill, TTFT 9.646 ms (13 Laufe)AMD Radeon 8060S Grap...NVIDIA GeForce RTX 2060 - 27,5 tok/s Generation, 62 tok/s Prefill, TTFT 180.818 ms (3 Laufe)NVIDIA GeForce RTX 20...CPU-only - 4,3 tok/s Generation, 62 tok/s Prefill, TTFT 31.435 ms (1 Lauf)CPU-onlyNVIDIA RTX SPARK (N1X) - 142,0 tok/s Generation, 2.336 tok/s Prefill, TTFT 5.494 ms (4 Laufe) | DIESER LAUF★ NVIDIA RTX SPARK (N1X)
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.499,4 tok/sNVIDIA GeForce RTX 5090 1.409,4 tok/sNVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.367,3 tok/sNVIDIA GeForce RTX 3090 Ti 852,0 tok/sNVIDIA RTX A6000 800,4 tok/sAMD Radeon RX 7900 XTX 450,5 tok/sNVIDIA GeForce RTX 3090 341,5 tok/sAMD Radeon PRO W7900 Dual Slot 296,2 tok/sAMD Radeon AI PRO R9700 271,4 tok/sAMD Radeon PRO W7800 48GB 235,5 tok/sNVIDIA Tesla V100 PCIe 32GB 225,9 tok/sNVIDIA DGX SPARK (GB10) 169,4 tok/sNVIDIA GeForce RTX 5070 Ti 142,9 tok/s★ NVIDIA RTX SPARK (N1X) 142,0 tok/s this runIntel Arc Pro B70 124,5 tok/sAMD Radeon 8060S Graphics 98,3 tok/sNVIDIA GeForce RTX 2060 27,5 tok/sCPU-only 4,3 tok/s

CPUby processor

1.9481.4619744870,005.20710.41415.621Prefill (tok/s)Generation (tok/s)AMD Ryzen 5 5600X 6-Core Processor - 1.499,4 tok/s Generation, 4.233 tok/s Prefill, TTFT 6.373 ms (11 Laufe)AMD Ryzen 5 5600X 6-C...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 7 5800X3D 8-Core Processor - 1.409,4 tok/s Generation, 4.912 tok/s Prefill, TTFT 4.113 ms (3 Laufe)AMD Ryzen 7 5800X3D 8...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.367,3 tok/s Generation, 6.432 tok/s Prefill, TTFT 4.005 ms (9 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 852,0 tok/s Generation, 3.431 tok/s Prefill, TTFT 6.717 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 800,4 tok/s Generation, 7.042 tok/s Prefill, TTFT 12.485 ms (62 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 3955WX 16-Cores - 450,5 tok/s Generation, 3.098 tok/s Prefill, TTFT 6.304 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 296,2 tok/s Generation, 3.069 tok/s Prefill, TTFT 9.493 ms (33 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics - 225,9 tok/s Generation, 975 tok/s Prefill, TTFT 8.633 ms (3 Laufe)AMD Ryzen 3 PRO 3200G...AMD Ryzen 3 3100 4-Core Processor - 198,8 tok/s Generation, 3.170 tok/s Prefill, TTFT 3.226 ms (3 Laufe)AMD Ryzen 3 3100 4-Co...Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz - 181,7 tok/s Generation, 1.632 tok/s Prefill, TTFT 92.034 ms (6 Laufe)Intel(R) Xeon(R) CPU ...NVIDIA Grace - 169,4 tok/s Generation, 3.685 tok/s Prefill, TTFT 2.454 ms (11 Laufe)NVIDIA GraceAMD Ryzen 9 7945HX with Radeon Graphics - 124,5 tok/s Generation, 578 tok/s Prefill, TTFT 5.272 ms (7 Laufe)AMD Ryzen 9 7945HX wi...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 98,3 tok/s Generation, 863 tok/s Prefill, TTFT 9.646 ms (13 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 ...NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) - 142,0 tok/s Generation, 2.336 tok/s Prefill, TTFT 5.494 ms (4 Laufe) | DIESER LAUF★ NVIDIA RTX Spark N1X ...
AMD Ryzen 5 5600X 6-Core Processor 1.499,4 tok/sAMD Ryzen 9 9950X 16-Core Processor 1.489,1 tok/sAMD Ryzen 7 5800X3D 8-Core Processor 1.409,4 tok/sAMD Ryzen Threadripper PRO 9965WX 24-Cores 1.367,3 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 852,0 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 800,4 tok/sAMD Ryzen Threadripper PRO 3955WX 16-Cores 450,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 296,2 tok/sAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics 225,9 tok/sAMD Ryzen 3 3100 4-Core Processor 198,8 tok/sIntel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz 181,7 tok/sNVIDIA Grace 169,4 tok/s★ NVIDIA RTX Spark N1X (6144-core GPU, 20-core CPU) 142,0 tok/s this runAMD Ryzen 9 7945HX with Radeon Graphics 124,5 tok/sAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 98,3 tok/sIntel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz 4,3 tok/s

MBby mainboard

1.9301.4479654820,005.17610.35215.528Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING - 1.499,4 tok/s Generation, 5.098 tok/s Prefill, TTFT 3.903 ms (8 Laufe)ASUSTeK COMPUTER INC....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 - 1.367,3 tok/s Generation, 6.964 tok/s Prefill, TTFT 11.395 ms (71 Laufe)ASUSTeK COMPUTER INC....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)Meigao Innovation Tec...ASUSTeK COMPUTER INC. PRIME A520M-K - 830,5 tok/s Generation, 3.419 tok/s Prefill, TTFT 8.537 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 450,5 tok/s Generation, 3.071 tok/s Prefill, TTFT 9.227 ms (36 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING - 225,9 tok/s Generation, 2.073 tok/s Prefill, TTFT 5.930 ms (6 Laufe)ASUSTeK COMPUTER INC....Dell Inc. PowerEdge R820 - 181,7 tok/s Generation, 1.408 tok/s Prefill, TTFT 83.377 ms (7 Laufe)Dell Inc. PowerEdge R...ASUSTeK COMPUTER INC. GX10 - 169,4 tok/s Generation, 3.685 tok/s Prefill, TTFT 2.454 ms (11 Laufe)ASUSTeK COMPUTER INC....Shenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) - 124,5 tok/s Generation, 578 tok/s Prefill, TTFT 5.272 ms (7 Laufe)Shenzhen Meigao Elect...Bosgame AXB35-02 (BeyondMax Series) - 98,3 tok/s Generation, 863 tok/s Prefill, TTFT 9.646 ms (13 Laufe)Bosgame AXB35-02 (Bey...ASUS H7607BA - 142,0 tok/s Generation, 2.336 tok/s Prefill, TTFT 5.494 ms (4 Laufe) | DIESER LAUF★ ASUS H7607BA
ASUSTeK COMPUTER INC. ROG STRIX B550-A GAMING 1.499,4 tok/sASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.489,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.367,3 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 852,0 tok/sASUSTeK COMPUTER INC. PRIME A520M-K 830,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 450,5 tok/sASUSTeK COMPUTER INC. ROG STRIX X570-F GAMING 225,9 tok/sDell Inc. PowerEdge R820 181,7 tok/sASUSTeK COMPUTER INC. GX10 169,4 tok/s★ ASUS H7607BA 142,0 tok/s this runShenzhen Meigao Electronic Equipment Co.,Ltd DRFXI (MotherBoard Series) 124,5 tok/sBosgame AXB35-02 (BeyondMax Series) 98,3 tok/s

ENGby engine

1.7831.4741.1658565471.4414.3787.31610.254Prefill (tok/s)Generation (tok/s)vLLM - 952,8 tok/s Generation, 8.704 tok/s Prefill, TTFT 4.451 ms (48 Laufe)vLLMunbekannt - 830,5 tok/s Generation, 2.991 tok/s Prefill, TTFT 5.522 ms (10 Laufe)unbekanntllama.cpp - 1.499,4 tok/s Generation, 3.267 tok/s Prefill, TTFT 15.185 ms (120 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.499,4 tok/s this runvLLM 952,8 tok/sunbekannt 830,5 tok/s

DRVby driver

1.9331.4509674830,002.0474.0946.141Prefill (tok/s)Generation (tok/s)unbekannt - 1.499,4 tok/s Generation, 5.037 tok/s Prefill, TTFT 12.955 ms (156 Laufe)unbekanntNVIDIA 590.48.01 / CUDA 13.1 - 169,4 tok/s Generation, 3.685 tok/s Prefill, TTFT 2.454 ms (11 Laufe)NVIDIA 590.48.01 / CU...Intel 26.18.38308.4 - 124,5 tok/s Generation, 578 tok/s Prefill, TTFT 5.272 ms (7 Laufe)Intel 26.18.38308.4AMD 7.0.0-27-generic - 79,4 tok/s Generation, 2.349 tok/s Prefill, TTFT 1.000 ms (4 Laufe)AMD 7.0.0-27-generic
unbekannt 1.499,4 tok/sNVIDIA 590.48.01 / CUDA 13.1 169,4 tok/sIntel 26.18.38308.4 124,5 tok/sAMD 7.0.0-27-generic 79,4 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 %
🔌 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)– missing
Electricity (2 years)–
TCO (2 years)–
Output tokens (2 years)7.88B
☁️ 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

Qwen3.6-35B-A3BNVIDIA RTX SPARK (N1X)Qwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.6-35B-A3BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.6-35B-A3B3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
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.