xiconfjs

What is your hardware running GLM5.3?

Did you check your GPU for memory errors/defects?

Same here. Have a small gitea instance with cloned projects from github I‘m keeping in case the github version gets removed. Every few days there is an army of bots hammering my small vm with 40k req/min for 20 min straight. I had to install anubis to keep the instance online (while still slowed down).

only the local providers in Germany are forced to block it via DNS - 8.8.8.8 to the rescue

How many tps and size of ctx?

What is the weight?

Thank you. Ordered one to play around and see if this is a viable alternative.

Thanks

you should look into https://github.com/noonghunna/club-3090

You mean this? https://fai-project.org/FAIme/live/

Do you have any source for this? It‘s not about trust in your information but do get deeper into this topic.

\o/

What? How?

WTH, a 302 into a "mailto:" (search for "HTTP redirect" in the featured article) opens up my e-mail client without clicking a mailto link!? This seems wrong.

I tried man times but at least with its API active, LMStudio has some kind of memory leaks which will slow down the whole system (after ~1-2 days of uptime) even after unloading the model and stopping LMStudio up to a point where even playing a 1080p video results in frame drops. No such issues with Ollama.

* macOS 26.x on MacBookPro M1 Max 32GB * Ollama on macOS, cursor to play around * Open WebUI [1] on my Homeserver via API to Ollama (also for remote „A.I.“ access) * running gpt-oss:20b, qwen3.5:9b with ease, qwen3.5:27b for more complex tasks

[1] https://github.com/open-webui/open-webui

Ollama on MacOS is a one-click solution with stable obe-click updates. Happy so far. But the mlx support was the only missing piece for me.

I waited a minute until my phone got hot.

What's My JND? 0.0032 Can you beat it? https://www.keithcirkel.co.uk/whats-my-jnd/?r=AUEjKP___831 #WhatsMyJND

I need a better display for sure :)

This is the only reason I stick to Terminator, but none of the othet terminal emulators are coming close. I wouldn‘t even be searching for an alternative if Terminator wouldn‘t crash every other week.

Except if you are living in a region where electricity is quite expensive :/

fewer competitors every year...Sony gave up as well :/

DBSM :D

Like what the internet was before advertising? ;)

But its english-only - so what else could you have tried? Asking because I‘m interested in a german version :)

„just like the gypsy woman said“

Not here in Germany - our T-Mobile Business access only gets a static IPv6 and our main fiber uplink from Telekom (same provider) gets both.

My person experience: if I can find a solution on stackoverflow etc. the LLM will produce working and fundamentally correct code. If I can‘t find a already fullfilled solution on these sites, the LLM is hallucinating like crazy (newer existing functions/modules/plugins, protocol features which aren’t specified and even github-repos which never existed). So, as stated my many people online before: for low-hanging fruits LLM are totally viable solution.

Isn‘t sub-1500 bytes the norm for residential internet access? (DOCSIS and DSL with PPPoE are the most common access protocols here in Germany)