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

Laguna-S-2.1-INT4

Performance benchmark · measured on 28.07.2026 11:50

Benchmark-IDrun-20260728-140954-000774
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: INT4
Generation461,99tok/s
Prefill3.219,05tok/s
Time to First Token6.266,00ms
Total duration47,64s
Concurrency5parallel
Ranking in the field
19of 34 systems

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

This run is better than 45 % of all comparable systems.
Generation 462,0 tok/s
-18 % vs Ø 560,7
Prefill 3.219,1 tok/s
-71 % vs Ø 11.259,0
Time to First Token 6.266 ms
-66 % vs Ø 18.245
Distribution in the field0 – 1.349 tok/s
Ø 561 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
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
gemma-4-E4B-itNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260727-181607-bf4219
914,3 tok/s
North-Mini-Code-1.0NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-164528-cc3069
876,1 tok/s
gpt-oss-20bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260723-194447-1679c5
842,9 tok/s
gpt-oss-120bNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140953-39e113
765,2 tok/s
Qwen3-Coder-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004605-81e02e
676,8 tok/s
Qwen3-VL-30B-A3B-InstructNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004607-0c918b
666,5 tok/s
Qwen3-30B-A3B-Instruct-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004604-c65af3
649,0 tok/s
Qwen3-30B-A3B-Thinking-2507NVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260724-004605-09fb68
625,7 tok/s
Laguna-S-2.1-INT4 this runNVIDIA RTX PRO 6000 Blackwell Workstation Edition · run-20260728-140954-000774
462,0 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: INT4
Model: Laguna-S-2.1-INT4

Configuration

benchmark-konfiguration — run-20260728-140954-000774
# LLM-Benchmark Konfiguration # Modell : Laguna-S-2.1-INT4 # Engine : llama.cpp # Run-ID : run-20260728-140954-000774 # 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--Laguna-S-2.1-GGUF/snapshots/750f92f90cf54159c4d7a610cb7b3e74498e75c6/UD-Q4_K_M/Laguna-S-2.1-UD-Q4_K_M-00001-of-00003.gguf \ --alias Laguna-S-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-S-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--unsloth--Laguna-S-2.1-GGUF/snapshots/750f92f90cf54159c4d7a610cb7b3e74498e75c6/UD-Q4_K_M/Laguna-S-2.1-UD-Q4_K_M-00001-of-00003.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-S-2.1-INT4 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

1.0287715142570,002.2364.4726.708Prefill (tok/s)Generation (tok/s)AMD Radeon AI PRO R9700 - 70,5 tok/s Generation, 5.430 tok/s Prefill, TTFT 5.742 ms (2 Laufe)AMD Radeon AI PRO R97...NVIDIA GeForce RTX 5070 Ti - 42,3 tok/s Generation, 139 tok/s Prefill, TTFT 136.435 ms (3 Laufe)NVIDIA GeForce RTX 50...NVIDIA RTX PRO 6000 Blackwell Workstation Edition - 797,1 tok/s Generation, 3.418 tok/s Prefill, TTFT 11.177 ms (2 Laufe) | DIESER LAUF★ NVIDIA RTX PRO 6000 B...
★ NVIDIA RTX PRO 6000 Blackwell Workstation Edition 797,1 tok/s this runAMD Radeon AI PRO R9700 70,5 tok/sNVIDIA GeForce RTX 5070 Ti 42,3 tok/s

CPUby processor

1.0287715142570,002.2364.4726.708Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 7955WX 16-Cores - 70,5 tok/s Generation, 5.430 tok/s Prefill, TTFT 5.742 ms (2 Laufe)AMD Ryzen Threadrippe...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 42,3 tok/s Generation, 139 tok/s Prefill, TTFT 136.435 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 9950X 16-Core Processor - 797,1 tok/s Generation, 3.418 tok/s Prefill, TTFT 11.177 ms (2 Laufe) | DIESER LAUF★ AMD Ryzen 9 9950X 16-...
★ AMD Ryzen 9 9950X 16-Core Processor 797,1 tok/s this runAMD Ryzen Threadripper PRO 7955WX 16-Cores 70,5 tok/sAMD Ryzen Threadripper PRO 5975WX 32-Cores 42,3 tok/s

MBby mainboard

1.0287715142570,002.2364.4726.708Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 70,5 tok/s Generation, 5.430 tok/s Prefill, TTFT 5.742 ms (2 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 42,3 tok/s Generation, 139 tok/s Prefill, TTFT 136.435 ms (3 Laufe)ASUSTeK COMPUTER INC....ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI - 797,1 tok/s Generation, 3.418 tok/s Prefill, TTFT 11.177 ms (2 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
★ ASUSTeK COMPUTER INC. ProArt X870E-CREATOR WIFI 797,1 tok/s this runASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 70,5 tok/sASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 42,3 tok/s

ENGby engine

1.0227675112560,04082.4304.4516.472Prefill (tok/s)Generation (tok/s)vLLM - 70,5 tok/s Generation, 5.430 tok/s Prefill, TTFT 5.742 ms (2 Laufe)vLLMllama.cpp - 797,1 tok/s Generation, 1.450 tok/s Prefill, TTFT 86.332 ms (5 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 797,1 tok/s this runvLLM 70,5 tok/s

DRVby driver

8778377977577172.4322.5362.6392.743Prefill (tok/s)Generation (tok/s)unbekannt - 797,1 tok/s Generation, 2.587 tok/s Prefill, TTFT 63.306 ms (7 Laufe)unbekannt
unbekannt 797,1 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (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 0.12
Token / kWh2.58M
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)29.14B
☁️ 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

Laguna-S-2.1-INT4NVIDIA RTX PRO 6000 Blackwell Workstation EditionLaguna-S-2.1-INT43x AMD Radeon AI PRO R9700Laguna-S-2.1-INT4NVIDIA GeForce RTX 5070 Ti
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.