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

Qwen3.6-27B

Performance benchmark · measured on 29.07.2026 00:09

Benchmark-IDrun-20260729-032122-bd199f
Timebench 3 - Kombi (Prefill + Generation)Dense27BRuntime: llama.cppQuantisierung: Q4_K_M
Generation30,55tok/s
Prefill441,71tok/s
Time to First Token56.170,00ms
Total duration649,18s
Concurrency5parallel
Ranking in the field
269of 331 systems

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

This run is better than 19 % of all comparable systems.
Generation 30,6 tok/s
-92 % vs Ø 361,9
Prefill 441,7 tok/s
-92 % vs Ø 5.274,4
Time to First Token 56.170 ms
+130 % vs Ø 24.397
Distribution in the field0 – 1.349 tok/s
Ø 361 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
gemma-4-E2B-itNVIDIA GeForce RTX 5090 · run-20260728-184455-5b4937
1.301,9 tok/s
gemma-4-E2B-it3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-184456-4111a9
1.195,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-30d864
1.188,7 tok/s
NVIDIA-Nemotron-3-Nano-4BNVIDIA GeForce RTX 5090 · run-20260728-194135-5432cd
1.164,8 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-9e81f9
1.136,3 tok/s
gpt-oss-20bNVIDIA GeForce RTX 5090 · run-20260729-032121-058a31
1.113,5 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-836a91
1.090,6 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-b8a818
1.071,0 tok/s
NVIDIA-Nemotron-3-Nano-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-194136-038e92
1.051,1 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260729-032121-ffb18a
1.015,5 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
Qwen3.6-27B this runNVIDIA GeForce RTX 5070 Ti · run-20260729-032122-bd199f
30,6 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: NVIDIA GeForce RTX 5070 Ti · 16 GB VRAM
CPU: AMD Ryzen Threadripper PRO 5975WX 32-Cores
RAM: 247 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI

Setup

Runtime: llama.cpp
Quantization: Q4_K_M
Model: Qwen3.6-27B

Configuration

benchmark-konfiguration — run-20260729-032122-bd199f
# LLM-Benchmark Konfiguration # Modell : Qwen3.6-27B # Engine : llama.cpp # Run-ID : run-20260729-032122-bd199f # GPU : NVIDIA GeForce RTX 5070 Ti # CPU : AMD Ryzen Threadripper PRO 5975WX 32-Cores # RAM : 247 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--DavidAU--Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF/snapshots/ee5b7441ffe27869e1e5b4357733248d561c26b7/Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-Q4_K_M.gguf \ --alias Qwen3.6-27B \ --host 0.0.0.0 \ --port 8000 \ -ngl 30 \ -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.Qwen3.6-27B
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--DavidAU--Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF/snapshots/ee5b7441ffe27869e1e5b4357733248d561c26b7/Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-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.30
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

Qwen3.6-27B 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

7065293531760,001.1092.2183.327Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 546,9 tok/s Generation, 2.739 tok/s Prefill, TTFT 9.126 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 264,2 tok/s Generation, 1.458 tok/s Prefill, TTFT 19.358 ms (3 Laufe)NVIDIA GeForce RTX 30...AMD Radeon 8060S Graphics - 25,6 tok/s Generation, 381 tok/s Prefill, TTFT 15.150 ms (2 Laufe)AMD Radeon 8060S Grap...NVIDIA GeForce RTX 5070 Ti - 57,2 tok/s Generation, 447 tok/s Prefill, TTFT 80.318 ms (3 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 546,9 tok/sNVIDIA GeForce RTX 3090 Ti 264,2 tok/s★ NVIDIA GeForce RTX 5070 Ti 57,2 tok/s this runAMD Radeon 8060S Graphics 25,6 tok/s

CPUby processor

7065293531760,001.1092.2183.327Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 546,9 tok/s Generation, 2.739 tok/s Prefill, TTFT 9.126 ms (3 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 9 8945HX with Radeon Graphics - 264,2 tok/s Generation, 1.458 tok/s Prefill, TTFT 19.358 ms (3 Laufe)AMD Ryzen 9 8945HX wi...AMD RYZEN AI MAX+ 395 w/ Radeon 8060S - 25,6 tok/s Generation, 381 tok/s Prefill, TTFT 15.150 ms (2 Laufe)AMD RYZEN AI MAX+ 395...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 57,2 tok/s Generation, 447 tok/s Prefill, TTFT 80.318 ms (3 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 546,9 tok/sAMD Ryzen 9 8945HX with Radeon Graphics 264,2 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 57,2 tok/s this runAMD RYZEN AI MAX+ 395 w/ Radeon 8060S 25,6 tok/s

MBby mainboard

7065293531760,001.1092.2183.327Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 546,9 tok/s Generation, 2.739 tok/s Prefill, TTFT 9.126 ms (3 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 264,2 tok/s Generation, 1.458 tok/s Prefill, TTFT 19.358 ms (3 Laufe)Meigao Innovation Tec...Bosgame AXB35-02 (BeyondMax Series) - 25,6 tok/s Generation, 381 tok/s Prefill, TTFT 15.150 ms (2 Laufe)Bosgame AXB35-02 (Bey...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 57,2 tok/s Generation, 447 tok/s Prefill, TTFT 80.318 ms (3 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 546,9 tok/sMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 264,2 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 57,2 tok/s this runBosgame AXB35-02 (BeyondMax Series) 25,6 tok/s

ENGby engine

6025745475204921.2551.3091.3621.416Prefill (tok/s)Generation (tok/s)llama.cpp - 546,9 tok/s Generation, 1.336 tok/s Prefill, TTFT 32.428 ms (11 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 546,9 tok/s this run

DRVby driver

6025745475204921.2551.3091.3621.416Prefill (tok/s)Generation (tok/s)unbekannt - 546,9 tok/s Generation, 1.336 tok/s Prefill, TTFT 32.428 ms (11 Laufe)unbekannt
unbekannt 546,9 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 10 W
⚡ TDP 310 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)310 W estimated (TDP)GPU 300 + Board 10 W full load
Avg cost / hourEUR 0.093
Electricity / 1M tokensEUR 0.85
Token / kWh354.77K
Acquisition (system)EUR 2,126 missingRAM EUR 1,976 · PSU EUR 150
Electricity (2 years)
TCO (2 years)EUR 3,755
Output tokens (2 years)1.93B
☁️ 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 (10 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

Qwen3.6-27BNVIDIA GeForce RTX 5070 TiQwen3.6-27BNVIDIA RTX PRO 6000 Blackwell Workstation EditionQwen3.6-27BNVIDIA GeForce RTX 3090 TiQwen3.6-27BAMD 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.