Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
Contributed byMario AlkaPoolside

Laguna-XS-2.1

Performance benchmark · measured on 28.07.2026 11:54

Benchmark-IDrun-20260728-140954-70b862
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: INT4
Generation875,59tok/s
Prefill11.578,09tok/s
Time to First Token2.411,50ms
Total duration23,50s
Concurrency5parallel
Ranking in the field
13of 189 systems

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

This run is better than 94 % of all comparable systems.
Generation 875,6 tok/s
+207 % vs Ø 284,9
Prefill 11.578,1 tok/s
+120 % vs Ø 5.264,8
Time to First Token 2.412 ms
-91 % vs Ø 25.716
Distribution in the field0 – 1.349 tok/s
Ø 283 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-4B3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260727-181606-8b381e
1.077,4 tok/s
gpt-oss-20b3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-034052-437388
989,7 tok/s
Laguna-XS-2.1 same modelNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-17e7b6
975,1 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5070 Ti · run-20260727-032758-a7d32d
973,5 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5070 Ti · run-20260727-090152-b472f0
971,4 tok/s
gemma-4-E2B-itNVIDIA GeForce RTX 5070 Ti · run-20260728-140953-67115b
969,6 tok/s
Laguna-XS-2.1 same modelNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-d94e39
967,9 tok/s
Laguna-XS-2.1 same modelNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140955-8dd350
966,1 tok/s
gemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bf4219
914,3 tok/s
Laguna-XS-2.1 this run3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-140954-70b862
875,6 tok/s
Laguna-XS-2.1 same model3× NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · run-20260728-140954-b4169e
871,8 tok/s

How does this benchmark compare on other GPUs?

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

Hardware

GPU: 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition · 96 GB VRAM
CPU: AMD Ryzen Threadripper PRO 9965WX 24-Cores
RAM: 125 GB
Mainboard: ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE

Setup

Runtime: llama.cpp
Quantization: INT4
Model: Laguna-XS-2.1

Configuration

benchmark-konfiguration — run-20260728-140954-70b862
# LLM-Benchmark Konfiguration # Modell : Laguna-XS-2.1 # Engine : llama.cpp # Run-ID : run-20260728-140954-70b862 # GPU : 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition # CPU : AMD Ryzen Threadripper PRO 9965WX 24-Cores # RAM : 125 GB bench@llm-benchmark:~$ /home/godcore/llama.cpp/build/bin/llama-server \ -m /home/godcore/.cache/huggingface/hub/models--poolside--Laguna-XS-2.1-GGUF/snapshots/1a37c0a5fb8c7a18e6106decb6be6327d1b63fa6/Laguna-XS-2.1-Q4_K_M.gguf \ --alias Laguna-XS-2.1-INT4 \ --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.Laguna-XS-2.1-INT4
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--poolside--Laguna-XS-2.1-GGUF/snapshots/1a37c0a5fb8c7a18e6106decb6be6327d1b63fa6/Laguna-XS-2.1-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

Laguna-XS-2.1 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

2.2541.6901.1275630,005.00210.00515.007Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 1.757,4 tok/s Generation, 7.536 tok/s Prefill, TTFT 3.531 ms (9 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 986,1 tok/s Generation, 4.490 tok/s Prefill, TTFT 6.230 ms (9 Laufe)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 319,0 tok/s Generation, 1.407 tok/s Prefill, TTFT 29.330 ms (6 Laufe)NVIDIA GeForce RTX 50...AMD Radeon AI PRO R9700 - 154,3 tok/s Generation, 8.941 tok/s Prefill, TTFT 3.080 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 1.615,3 tok/s Generation, 12.307 tok/s Prefill, TTFT 4.796 ms (6 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 1.757,4 tok/s★ NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 1.615,3 tok/s this runNVIDIA GeForce RTX 3090 Ti 986,1 tok/sNVIDIA GeForce RTX 5070 Ti 319,0 tok/sAMD Radeon AI PRO R9700 154,3 tok/s

CPUby processor

2.2541.6901.1275630,005.00210.00515.007Prefill (tok/s)Generation (tok/s)AMD Ryzen 9 9950X 16-Core Processor - 1.757,4 tok/s Generation, 7.536 tok/s Prefill, TTFT 3.531 ms (9 Laufe)AMD Ryzen 9 9950X 16-...AMD Ryzen 9 8945HX with Radeon Graphics - 986,1 tok/s Generation, 4.490 tok/s Prefill, TTFT 6.230 ms (9 Laufe)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 319,0 tok/s Generation, 1.407 tok/s Prefill, TTFT 29.330 ms (6 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 7955WX 16-Cores - 154,3 tok/s Generation, 8.941 tok/s Prefill, TTFT 3.080 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 9965WX 24-Cores - 1.615,3 tok/s Generation, 12.307 tok/s Prefill, TTFT 4.796 ms (6 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen 9 9950X 16-Core Processor 1.757,4 tok/s★ AMD Ryzen Threadripper PRO 9965WX 24-Cores 1.615,3 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 986,1 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 319,0 tok/sAMD Ryzen Threadripper PRO 7955WX 16-Cores 154,3 tok/s

MBby mainboard

2.2211.6661.1105550,004.6559.30913.964Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 1.757,4 tok/s Generation, 7.536 tok/s Prefill, TTFT 3.531 ms (9 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 986,1 tok/s Generation, 4.490 tok/s Prefill, TTFT 6.230 ms (9 Laufe)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 319,0 tok/s Generation, 1.407 tok/s Prefill, TTFT 29.330 ms (6 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 1.615,3 tok/s Generation, 11.466 tok/s Prefill, TTFT 4.367 ms (8 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 1.757,4 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 1.615,3 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 986,1 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 319,0 tok/s

ENGby engine

2.2541.6901.1275630,05.3486.8808.4129.944Prefill (tok/s)Generation (tok/s)vLLM - 154,3 tok/s Generation, 8.941 tok/s Prefill, TTFT 3.080 ms (2 Laufe)vLLMllama.cpp - 1.757,4 tok/s Generation, 6.351 tok/s Prefill, TTFT 9.753 ms (30 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 1.757,4 tok/s this runvLLM 154,3 tok/s

DRVby driver

1.9331.8451.7571.6701.5826.1226.3826.6436.903Prefill (tok/s)Generation (tok/s)unbekannt - 1.757,4 tok/s Generation, 6.513 tok/s Prefill, TTFT 9.336 ms (32 Laufe)unbekannt
unbekannt 1.757,4 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 165 W
⚡ TDP 983 W
☁️ External LLM (API)
Electricity0.30 EUR/kWh
Avg power (incl. idle)983 W estimated (TDP)GPU 900 + CPU 57 + Board 25 W full load
Avg cost / hourEUR 0.29
Electricity / 1M tokensEUR 0.094
Token / kWh3.21M
Acquisition (system)EUR 45,748 full priceGPU EUR 39,000 · CPU EUR 3,499 · Board EUR 1,299 · RAM EUR 1,750 · PSU EUR 200
Electricity (2 years)
TCO (2 years)EUR 50,912
Output tokens (2 years)55.23B
☁️ 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 (165 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

Laguna-XS-2.13x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionLaguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation EditionLaguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell Workstation EditionLaguna-XS-2.1NVIDIA RTX PRO 6000 Blackwell 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.