N8N VPS Configuration for AgentAI

[terryble66]

Describe the problem/error/question

I have a VPS with this configuration from Hostinger (KVM 2):
2 cœurs vCPU
8 Go de RAM
100 Go d’espace disque NVM
8 To de bande passante

What is the error message (if any)?

The last 3 tries were with three different model
llama , deepseek and mistral

Each one took 1m30 to 2m40 to reply

root@srv999:~# docker stats --no-stream | grep ollama
d73ca1352b23 ollama 104.76% 2.416GiB / 7.755GiB 31.15% 208kB / 395kB 61.1GB / 1.37GB 16
root@srv718602:~#

I create a swap not sure if it’s good please let me no as well
root@srv999:~# free -h
total used free shared buff/cache available
Mem: 7.8Gi 1.2Gi 1.4Gi 6.8Mi 5.5Gi 6.6Gi
Swap: 2.0Gi 1.0Gi 1.0Gi

• Swap total : 2.0 GiB
• Swap used : 1.0 GiB

Can you lead me to optimize my agent please ?

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your n8n setup

• n8n version: : n8n Version: 1.77.3
• Database (default: SQLite): postgresdb
• **n8n EXECUTIONS_PROCESS setting : main
• **Running n8n via : Docker
• **Operating system: Ubuntu 24.04.2 LTS
• **Docker : version 27.5.1, build 9f9e405
• **Docker Compose version v2.32.4
• **git version 2.43.0

[n8n]

It looks like your topic is missing some important information. Could you provide the following if applicable.

• n8n version:
• Database (default: SQLite):
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• Running n8n via (Docker, npm, n8n cloud, desktop app):
• Operating system:

[Alex_Huang]

@terryble66 what kind of problem, bro ?

[Akram]

What kind of models are you trying to run? Any models with more than 7b parameters will usually be very slow on a system without a GPU like your VPS.

[terryble66]

Well I used à special git from someone. I will restart my n8n from scratch with the n8n git and give it another try.