/home/chiefgyk3d
Region: US
Thursday 02 April 2026 19:01:03 GMT
13154
397
21
23
Music
Download
Comments
acrxhd :
I used Tailscale for my OpenWebUI. Probably not the most secure but it’s worked for my use case
2026-04-02 19:28:01
7
Veronica Dax :
I'm addicted to vibe coding overly specific functions for owui 😅 what models are you running?
2026-04-02 19:55:09
3
OpenclawGateway :
Bro... Just run two rtx5060ti 16gb for 32gb total vram. Then run Ollama split and you can run qwen3.6:35b with openclaw. Link in bio.
2026-06-28 15:23:43
0
Daniel Ebben :
tailscale?
2026-04-03 14:15:01
0
Martin :
yeah I did this yesterday but with tailscale and llama.cpp. I had speech to text/text to speech on one card and qwen on the other.
2026-04-26 05:30:46
0
Athion :
I’ve got LM Studios on the PC, and Ollama and LM Studios on the Mac, both feed to OpenWebUI … and I have a HomeHub (locally running webpage that accesses most of my apps that I’ve written) … everything accessible by my phone over Tailscale. Oh! And I built a memory server for Claude Code that the Mac and PC can both reach… so they can share memories. Makes building apps on both machines a LOT easier. Isn’t it a great time to be alive?
2026-04-03 01:22:34
0
Therakeets :
how frustrating are the inconsistencies in running locally with smaller llms.
2026-04-03 14:47:56
0
Ratozumbi :
I hear this video dubbed to my language (Portuguese) what is happening? How can i prevent this from happening?
2026-04-03 16:45:02
0
mcserverinferno :
what could a man with your experience and skills possibly need ollama for? serious question
2026-04-18 11:31:12
0
MotoLifeMyke :
And I use negate that opens up 2 separate t-thrust modules to run in tandem 3 LML’s so I can hyperlink to the web without any lag that’s totally encrypted and ready for any type of future server. 😊
2026-04-03 13:01:21
0
To see more videos from user @chiefgyk3d, please go to the Tikwm
homepage.
