@llm.guy: Homelabbing pt6, integrated basic Jarvis interface into proxmox Memory + Full Toolset next? #homelab #proxmox #jarvis #selfhosted #ollama

randomuser1737482 :

What machine do you use for your LLMs? GPU?

LIS10INC :

Same setup for me. Kubernetes and docker/portainer make distributing workload a live setup with yaml files.

FirestormTD :

Yo how do u get the icons on the vms or rename them

☦︎ bigfanofbears ☦︎ :

wow just thought of this and im 3 months late

rufus :

could you use a wireguard vpn to interact with the web ui on a remote device outside of you lan?

esp32cam :

A few days ago, I upgraded Proxmox to version 9.0-1 following the official instructions. Unfortunately, everything was lost. 4 VMs. I had planned to choose Proxmox as the main virtualization platform for the company’s production environment, but in the end, I decided to go with Hyper-V on Windows 2025. It’s more reliable and stable. I also currently have VMware running in the production environment, operating flawlessly and without interruption since 2016.💪

Connor ✟ :

I’m half tempted to throw proxmox onto my ace magic mini pc (my main server in the cluster)

meilleur102 :

do you have the link for the LLM?

Boundzero :

this is awesome. Im hoping to see any sort of LLM that I could run on my phone remotely that active listens and couldn't respond to questions via like Bluetooth. would be so great at my job

Playboiallen07 :

So I have a physical server for all those 🤦🏾‍♂️is there a recommended way to connect / monitor all my devices like this GUI?

BigChris :

Do you have Jarvis hooked into your HA yet? I’m trying to figure out the best way to do that.

TCSMasked :

get a couple cheap raspberry pi 3’s and slap ubuntu on there and attach a microphone and speaker in rooms u want jarvis in

Eli Pothier :

Do u have shared storage for high availability or nah

eirikfnygard :

shanamzzz :

good work man

gator222222 :

Are you going to add rag to your llm through that interface? If so can you show how?

CloudX0520 :

* insert SpongeBob I DONT NEEEEEDDDDD ITTTTT*

️ :

do you use these for the proxmox servers? I'm tryna make a cluster myself

zettan86 :

hi again. so i have decided to set up local but i am stuck. downloaded oobabooga version 3.12 but i only get error on the llm i have chosen which is Meta-Llama-3-8B-Instruct.Q4_0.gguf and llama3-8b-q4_0? . do you think the llm models are too old to run with the latest oobabooga? love following your process 🙏🏽😃