Topic per title, basically.

For me: after setting up all the integrations and fall overs using the arr stack and Jellyfin (inc Sabnzdb etc)... I keep circling back to Nova video player.

https://github.com/nova-video-player/aos-AVP/releases

It's arguably not even self hosting...but there something undeniably cool about sticking a USB stick into a router, installing a single app on your TV and boom, done. EDIT: of course, it can consume the *arr stack, integrate with Ombi etc

IOW, I really like stuff that simple to set up and punches above its weight class.

Right - I see the other topic has been locked / author hasn't returned to follow community rules.

Here's the original topic https://news.ycombinator.com/item?id=49003386

and a measured (IMHO) response to it. (BTW, do your self a favour and change tabs with that site open :)

https://xn--gckvb8fzb.com/i-regret-migrating-to-codeberg/

It's a tough spot, Codeberg has found themselves in and I wish them luck. But beyond that, this is (yet) another reminder that in 2026, if you don't self host it, the cloud is just someone else computer

Hi all, if you've not heard, there's been a Caveman compression version of Qwen 3.6-27b and Qwen 3.6-35b-3ab.

https://huggingface.co/ProCreations/grug-27b-gguf

https://huggingface.co/ProCreations/grug-35b-v2

https://huggingface.co/ProCreations/grug-35b-v2-gguf

I've been playing around with 35B and I am able to run it on my ancient Quadro P1000 4gb at ~10tok/s.

But beyond that, the quality of the reasoning and the token discipline / output is actually higher than a stock, in my opinion.

You can read the benchmarks above; I am also uploading a HTML file here for your consideration.

(Sorry for the Limewire link; I dunno where else to share throw-away files. It's HTML, though the side by side probably works better if you actually download it)

Anyway...I'm doing more testing right now...but so far, this is a good cook.

Or -

Grug good. Me like.

Just wanted to share my review and experiences of using Lumo 2.0, which is Proton's new LLM.

Given that many of us use Proton services and are privacy conscious, I thought this might be of interest.

The below is a lightly edited from another post.

It broadly speaks to the integration (or lack thereof) of Lumo with other Proton services, rather than the privacy angle (which I am sure you're aware of), though I can speak to that too. EDIT: see my below follow up.

I see no reason at this point to continue with my subscription, and if anything, I'm thankful for the shot in the arm to improve my self hosted stack / create an equivalent or better service for myself.

TL;DR: With some elbow grease and know how you can probably create something equivalent or better home.

I keep seeing suggestions here that Proton should adopt Kimi K3, or otherwise move to a much larger and more fashionable model.

I am increasingly unconvinced that model capability is Lumo’s primary problem.

Lumo Lite appears very likely to be based on a Qwen 27B-class model, judging from the behaviour and the Artificial Analysis results Proton have stated.

(That identification is not proven, obviously, but it is plausible enough for my broader point).

A model in that class should already be an excellent all-round foundation for Lumo.

My humble suggestion:

Serve it at FP8 or comparable precision. Optimise it properly. Keep latency reasonable. Increase the context length.

Then spend the engineering effort on the things that would actually distinguish Lumo from every other chatbot:

• Reliable Proton Mail, Drive, Calendar and Contacts integration

• Authoritative and current Proton product information

• Deterministic tools for calculations, dates, prices, plan limits and account features

• Exact-span retrieval rather than loose paraphrasing for proton_info

• Visible source dates and document versions

• A clear distinction between retrieved evidence and the model’s interpretation.

At present, Lumo can (apparently) retrieve information about Proton’s own products and then produce an answer that reverses or mangles the source.

Something like “it is not $12.99” becoming “$12.99” is not a problem that Kimi K3 or GLM inherently solves.

It is a grounding and validation problem.

A larger model may paper over some failures. It may phrase uncertainty more elegantly. It may recover from poor retrieval more often.

But it does not make stale information current, and it does not make an unreliable tool pipeline deterministic.

IMESHO, Proton’s strategic advantage is not that it can host the largest open model.

Other companies will always have larger models, more compute and faster release cycles.

Its advantage is that it owns a private productivity ecosystem, with only one real mind share competitor.

A smaller model that can reliably search my mail, locate a Drive document, understand my calendar, retrieve the correct Proton support information, chat, OCR (native ability with latter Qwen models iirc), image manipulation and perform bounded actions would be considerably more useful than a stronger general-purpose chatbot with shallow integration.

I would much rather Proton solidify Lumo Lite into a dependable, deeply integrated assistant than keep changing the model underneath it in pursuit of benchmark gains.

The model is probably already good enough.

The product around it is not.

ICBW and YMMV.

https://www.meilisearch.com/docs/capabilities/full_text_search/overview

Broadly, how do you find it? Are its semantic search features useful? And have you found a way to have it search within PDFs?

Anything that I should know about it, any features you feel are fantastic or feel are lacking?

https://lemmy.world/post/49736885

If you follow AI news at all as part of your self-hosting interests, you may have become aware recently that open AI (the frontier lab between behind chat GPT) has admitted (loosely) culpability in an cyber attack against HuggingFace (the major repository of open-weight models.)

The details that present are somewhat sketchy, but the gist of it is that open AI seems to have given unrestricted access to a AI agent, which then attacked hugging face, who in a twist of deliciousness, used an open source agent to defend themselves.

I'd joke and tell you to make sure that you haven't left any open ports on your router, but if you're here reading this I think probably you know better than that.

Less comically, there's a weird intersection here between self-hosting, sovereignty and encroachment by big tech that is worth pay attention to.

It should certainly spur people on to seriously consider self-hosting as much of their infrastructure as they can (and securing it) if this is the preview of things to come.

Something is rotten in the state of Denmark.

I just wish I'd bought more SSDs.

Is there some way to have age rating or parental controls in the basic version of Streamio so that the kids don't end up getting SpongeBob intermingled with House of the Dragon?

I've tried Nuvio also, and while that gives a pin / user accounts, it doesn't stop kids from altering settings etc.

Ideally, I'd want a system like Jellyfin has. Is that possible?

PS: on Nuvio, I had the idea of removing all plugins bar this one for the kids account

https://kids.gstream.stream/manifest.json

so that it's at least obfuscated, but that plug in seems broken.

Hello.

Ive been using CloudStream for the last little while but my kids find it a little clunky.

I've installed Stremio today but am not clear as to how to tee it up with free pirate streams, ala CloudStream.

I've checked fmhy and the glanced at the mega thread, as well as asking my clankers.

Can someone point me in the direction of the equivalent of CloudStream's Mega plug in / repository for stremio?

EDIT: thank you to all. All the solutions you suggested worked, but in the end, it was just eaiest to pay for Real-Debrid.

OK, this is cool

https://www.instructables.com/Jcorp-Nomad-Mini-WIFI-Media-Server/

What is Jcorp Nomad?

Nomad is a self-contained, battery-friendly media server that fits in your pocket. 

It creates a local Wi-Fi hotspot with no internet connection needed, allowing you to stream your own movies, shows, music, books, and more directly from a microSD card. It’s perfect for camping, road trips, classrooms, or any scenario where connectivity is limited or unavailable.

TL;DR: Low power ESP-32 media server, that creates a local WiFi hotspot, media front end and serves upto 8 streams simultaneously.

Disclosure: no affiliation with project, other than wishing I'd thought of it first. I love me some ESP-32 black magic.

I promise I wasn't reading it, I was traveling across it.

I'm big on retro tech (which, sadly, is becoming code for credit bills in a trenchcoat; why did I give all that good shit away :( ) and occasionally think "damn, I should try to get an old C64 or Amiga, specc it up and use it as a daily driver".

Then I got to wondering "do folks still use retro PCs to self host cool stuff?"

So, do folks here still use retro computers for self-hosting- either actually hosting services on the old hardware, or self-hosting lightweight tools specifically for use from vintage machines?

FYI Lumo 2.0 just dropped and it seems to be comprised of open weight models (GLM 5.2 as the big model, Qwen 3.6 35B as the small, few others to boot)

https://proton.me/support/lumo-privacy

Having played around with it a bit...I dunno. It seems pretty locked down / security theatre heavy / refusals on benign things.

I can't run GLM locally (who can lol) but all things given I dunno how good value for money it is vs other options.

(Security and privacy promises notwithstanding that is - which perhaps, are the whole point with Lumo).

Has anyone used Lumo for any period of time? What quants do they use?