Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
DEEN
Sign in Sign up
Beta
Contributed byMario AlkaPoolside

Laguna-S-2.1-INT4

Performance benchmark · measured on 28.07.2026 00:26

Benchmark-IDrun-20260728-034053-edab0e
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: INT4
Generation12,62tok/s
Prefill130,06tok/s
Time to First Token21.117,50ms
Total duration204,56s
Concurrency1parallel
Ranking in the field
This GPUAll GPUs
12of 23 systems

Performance benchmark · Primary metric: Generation-Speed (tok/s) · 1× concurrent

This run is better than 50 % of all comparable systems.
Generation 12,6 tok/s
-78 % vs Ø 57,6
Prefill 130,1 tok/s
-93 % vs Ø 1.787,7
Time to First Token 21.118 ms
+71 % vs Ø 12.359
Distribution in the field2 – 242 tok/s
Ø 58 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

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: INT4
Model: Laguna-S-2.1-INT4

Configuration

benchmark-konfiguration — run-20260728-034053-edab0e
# LLM-Benchmark Konfiguration # Modell : Laguna-S-2.1-INT4 # Engine : llama.cpp # Run-ID : run-20260728-034053-edab0e # 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--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 0 \ -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.0
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

83,269,856,443,029,602.2364.4726.708Prefill (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) | DIESER LAUF★ NVIDIA GeForce RTX 50...
AMD Radeon AI PRO R9700 70,5 tok/s★ NVIDIA GeForce RTX 5070 Ti 42,3 tok/s this run

CPUby processor

83,269,856,443,029,602.2364.4726.708Prefill (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) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 7955WX 16-Cores 70,5 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 42,3 tok/s this run

MBby mainboard

83,269,856,443,029,602.2364.4726.708Prefill (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) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 70,5 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 42,3 tok/s this run

ENGby engine

83,269,856,443,029,602.2364.4726.708Prefill (tok/s)Generation (tok/s)vLLM - 70,5 tok/s Generation, 5.430 tok/s Prefill, TTFT 5.742 ms (2 Laufe)vLLMllama.cpp - 42,3 tok/s Generation, 139 tok/s Prefill, TTFT 136.435 ms (3 Laufe) | DIESER LAUF★ llama.cpp
vLLM 70,5 tok/s★ llama.cpp 42,3 tok/s this run

DRVby driver

77,674,070,567,063,52.1202.2102.3012.391Prefill (tok/s)Generation (tok/s)unbekannt - 70,5 tok/s Generation, 2.255 tok/s Prefill, TTFT 84.158 ms (5 Laufe)unbekannt
unbekannt 70,5 tok/s
💰 Economics

Economics of this run

Operating cost, TCO and comparison with the next-best runs of the same model at identical concurrency (1× 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 2.05
Token / kWh146.55K
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)795.97M
☁️ 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

Laguna-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)–
NVIDIA GeForce RTX 5070 Ti · this run 13 tok/s

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.