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

Laguna-M.1

Performance benchmark · measured on 27.07.2026 22:23

Benchmark-IDrun-20260728-034052-718717
Timebench 3 - Kombi (Prefill + Generation)Runtime: llama.cppQuantisierung: NVFP4
Generation5,86tok/s
Prefill66,43tok/s
Time to First Token40.934,00ms
Total duration431,78s
Concurrency1parallel
Ranking in the field
18of 23 systems

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

This run is better than 23 % of all comparable systems.
Generation 5,9 tok/s
-90 % vs Ø 57,6
Prefill 66,4 tok/s
-96 % vs Ø 1.787,7
Time to First Token 40.934 ms
+231 % vs Ø 12.359
Distribution in the field2 – 242 tok/s
Ø 58 Median Dieser Lauf

Wie schlägt sich dieser Benchmark mit anderen Modellen?

How does this benchmark compare on other GPUs?

Same model on different hardware · 1× 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: NVFP4
Model: Laguna-M.1

Configuration

benchmark-konfiguration — run-20260728-034052-718717
# LLM-Benchmark Konfiguration # Modell : Laguna-M.1 # Engine : llama.cpp # Run-ID : run-20260728-034052-718717 # 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--linuxid10t--Laguna-M.1-GGUF/snapshots/3b5ee482c6894f80e696058271ea86d80ffcb848/Laguna-M.1-Q4_K_M.gguf \ --alias Laguna-M.1-NVFP4 \ --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-M.1-NVFP4
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--linuxid10t--Laguna-M.1-GGUF/snapshots/3b5ee482c6894f80e696058271ea86d80ffcb848/Laguna-M.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.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-M.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

4393292191100,007781.5552.333Prefill (tok/s)Generation (tok/s)NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition - 337,6 tok/s Generation, 1.882 tok/s Prefill, TTFT 17.267 ms (3 Laufe)NVIDIA RTX PRO 6000 B...NVIDIA GeForce RTX 3090 Ti - 1,8 tok/s Generation, 8 tok/s Prefill, TTFT 264.875 ms (1 Lauf)NVIDIA GeForce RTX 30...NVIDIA GeForce RTX 5070 Ti - 7,0 tok/s Generation, 60 tok/s Prefill, TTFT 116.585 ms (12 Laufe) | DIESER LAUF★ NVIDIA GeForce RTX 50...
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 337,6 tok/s★ NVIDIA GeForce RTX 5070 Ti 7,0 tok/s this runNVIDIA GeForce RTX 3090 Ti 1,8 tok/s

CPUby processor

4393292191100,007781.5552.333Prefill (tok/s)Generation (tok/s)AMD Ryzen Threadripper PRO 9965WX 24-Cores - 337,6 tok/s Generation, 1.882 tok/s Prefill, TTFT 17.267 ms (3 Laufe)AMD Ryzen Threadrippe...AMD Ryzen 9 8945HX with Radeon Graphics - 1,8 tok/s Generation, 8 tok/s Prefill, TTFT 264.875 ms (1 Lauf)AMD Ryzen 9 8945HX wi...AMD Ryzen Threadripper PRO 5975WX 32-Cores - 7,0 tok/s Generation, 60 tok/s Prefill, TTFT 116.585 ms (12 Laufe) | DIESER LAUF★ AMD Ryzen Threadrippe...
AMD Ryzen Threadripper PRO 9965WX 24-Cores 337,6 tok/s★ AMD Ryzen Threadripper PRO 5975WX 32-Cores 7,0 tok/s this runAMD Ryzen 9 8945HX with Radeon Graphics 1,8 tok/s

MBby mainboard

4393292191100,007781.5552.333Prefill (tok/s)Generation (tok/s)ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE - 337,6 tok/s Generation, 1.882 tok/s Prefill, TTFT 17.267 ms (3 Laufe)ASUSTeK COMPUTER INC....Meigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) - 1,8 tok/s Generation, 8 tok/s Prefill, TTFT 264.875 ms (1 Lauf)Meigao Innovation Tec...ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI - 7,0 tok/s Generation, 60 tok/s Prefill, TTFT 116.585 ms (12 Laufe) | DIESER LAUF★ ASUSTeK COMPUTER INC....
ASUSTeK COMPUTER INC. Pro WS WRX90E-SAGE SE 337,6 tok/s★ ASUSTeK COMPUTER INC. Pro WS WRX80E-SAGE SE WIFI 7,0 tok/s this runMeigao Innovation Technology (Shen Zhen) Co., Ltd DRFXL (MotherBoard Series) 1,8 tok/s

ENGby engine

371354338321304374390406422Prefill (tok/s)Generation (tok/s)llama.cpp - 337,6 tok/s Generation, 398 tok/s Prefill, TTFT 107.231 ms (16 Laufe) | DIESER LAUF★ llama.cpp
★ llama.cpp 337,6 tok/s this run

DRVby driver

371354338321304374390406422Prefill (tok/s)Generation (tok/s)unbekannt - 337,6 tok/s Generation, 398 tok/s Prefill, TTFT 107.231 ms (16 Laufe)unbekannt
unbekannt 337,6 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 4.41
Token / kWh68.05K
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)369.60M
☁️ 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-M.1NVIDIA GeForce RTX 5070 TiLaguna-M.13x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionLaguna-M.1NVIDIA GeForce RTX 5070 TiLaguna-M.1NVIDIA 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.