The only differences, if you didn’t know, is/was the friends you made along the journey.

Think really hard about what the letters “PC” are for us… That’s okay, we’ll wait…

Hint, it’s personal computer. A phone is technically a PC.

They are so lucky the manufacturer of those AT4 missiles are competent Swedes.

Ironically, I went from Pixel to Samsung, and legit enjoy the less hand-holding the Samsung flavored OS has with all the extra software settings and hardware features I never had with my Pixel.

It abstracts away llama.cpp in a way that, frankly, leaves a lot of performance and quality on the table.

OP, do you have any telemetry you can show us comparing the performance difference between what you setup on this guide and an Ollama setup? Otherwise, at face value, I’m going to assume this is another thing on the internet i have to assume is uncorroborated bullshit. Apologies for sounding rude.

I don’t like some things about the devs. I won’t rant, but I especially don’t like the hint they’re cooking up something commercial.

This concerns me. Please provide links for us to read here about this. I would like any excuse to uninstall Ollama. Thank you!

When I have £500 to spare, I’ll get that. Until then, my £60 Hauwei watch will do.

This is a very excellent comment, given the context and that this is an Android watch discussion and mine is not running Android.

What Huawei Android smart watch is fucking 60 Euros? I’ll buy it tonight.

I have a solar powered Garmin with all the biometrics and all the GPS protocols for every satellite system known to man, and a full map feature, same as any WearOS device is capable of, with zero installable apps; the watch lasts 21 days from a full charge.

I use it to tell me the time, reply to texts and track my workouts. Not sure the point of an entire linux kernel requiring to be run on other watches with only less than a single day of battery. It sounds preposterous that people are okay with this.

deleted by creator

I’m self hosting Vaultwarden and my home server got killed by the hurricane, yet I can still access my passwords just fine on the app because it stores them locally encrypted on my phone from the last time it synced. I just can’t update or change anything until I can bring everything back on.

So, host your own shit you cowards, it’ll be fine.

Yeah, either secure copy (SCP) or rsync are the ways to do this securely.

Why not use this and select whatever LLM to leverage as a RAG? It literally allows you to self host the model and select any model for both chat and RAG analysis. I have it set to Hermes3 8B for chat and a 1.3B Llama3 as the RAG.

That model is beautiful. Who is she?

Looks like a screenshot of a Counter Strike map.

You don’t even need a GPU, i can run Ollama Open-WebUI on my CPU with an 8B model fast af

Removed by mod

Ironically, if you ask ChatGPT to write you an initial system prompt for Hermes that will sound similar to its own, it will essentially share a trade secret with you and give up portions of its system prompt to make your 8B self hosted LLM perform like a commercial one.

Read up on Hermes3 technical paper and you’ll realize it’s the best one. Running 8B model with the correct initial system prompt makes it as smart as GPT4o

Correct, all VPN applications override the DNS server of any system it’s installed on.

pip is legit trash when trying to update modules

Removed by mod