SuspiciousCarrot78

FYI

If you use Gemma 4 E4B with llama.cpp, do yourself a favour and grab Google’s latest official chat template:

https://huggingface.co/google/gemma-4-E4B-it

https://huggingface.co/google/gemma-4-E4B-it/blob/main/chat_template.jinja

Use it with --jinja --chat-template-file chat_template.jinja.

The improvement in tool use is remarkable but it also seems to improve conversation continuity:

“Here is XYZ. Now add ABC. Now DEF. Actually, what were Y, B and C?”

That makes a big difference is multi step reasoning IME

Sadly, still no fixes for the other llama.cpp quirks.

• llama.cpp still reserves separate compute buffers for the target and MTP contexts, despite never using them concurrently.

That wastes about 1 GB of VRAM / causes OOM

PR #27489 fixes it, but remains not merged.

https://github.com/ggml-org/llama.cpp/pull/27489

• Audio also still fails through the llama.cpp WebUI.

The model itself can "hear". just fine - a direct curl request confirms that.

(“In this sound clip, the man says XYZ.”).

See #PR21825

https://github.com/ggml-org/llama.cpp/issues/21825

Dunno how these are resolved in other back ends / front ends, so just an FYI

I was reading a homelab discussion about NUTs (Network UPS Tools) that left me scratching my head and wondering "...why? Is complexity for complexities sake part of homelabs? Isn't this a huge overkill for one machine? Just...use a UPS? "

Then I got to thinking more broadly about homelabbing and I started to wonder if there weren't maybe (at least) two different schools of thought.

Using home media as example -

• Store the original.
• Detect the client.
• Transcode when required.
• Monitor the GPU.
• Add reverse proxy et al
• Track bandwidth.
• Add user accounts
• Add failover.
• Graph the result.
• Dashboard.

Vs

• Store a common compatible file for your devices.
• Play it directly.

Which school of thought are you and why?

PS: not throwing shade. I get it; for some people, complexity, learning infrastructure, practicing skills for work etc is part of the why. For me, complexity as recreation is suspiciously like work after work.

Perhaps there's an odd Venn diagram between homelabbing, interest in ownership / useful capability and infrastructure that could make for a fun discussion. For you, is homelabbing a means to an end or is it an end in itself?

EDIT: Feel free to consider "home-lab" and "self hosted" as synonyms for the purpose of this discussion (although I am aware they are somewhat different in scope).

...and this is why

1. pihole ain't enough
2. you dont buy skeezy shit off aliexpress
3. if your pirate box isn't self hosted, it's a prostitute :P

.

Honestly.... I'm kind of impressed at the level of fuckery that vSeeBox goes into. This is not just a random crypto mining bot... someone with real skills went to a fair bit of trouble to obfuscate things.

Impressive. Most impressive.

PS: don't buy vSeeBox - or do, with eyes wide open.

Right - ran a search and got no results, so am asking directly

This thing any good? Anyone run it?

https://circlus.org/

Use case: want to give my kid a SEVERELY locked down Moto E (2nd gen) as a Youtube music player device and a "message Daddy" app - strictly wifi / in house only.

The first thing is simple enough. The second thing is...interesting.

I had my local AI do some research and it spat out the above. I don't think it's quite right but It looks interesting. Any one use it / can comment? Failing that, can anyone recommend a simple WLAN messaging app that will run on Android 6 / lineageOS? I'm sure I can dig one up but if someone has one running, I'm all ears.

PS: I'm not looking at using a VPS for this...but the above did catch my attention as fairly normie friendly. Might be worth self hosting something like that...

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.

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.