Skip Navigation

Samskara

@ Samskara @sh.itjust.works

Posts
8
Comments
386
Joined
2 yr. ago

  • Microsoft is intentionally bricking all Office for Mac 2019/2021 installations

    Jump

  • On a Mac Apple‘s Office suite is the better choice.

  • Time to relax!

    Jump

  • She didn’t mention neet, so I’m good.

  • Tesla Solar Roof is on life support as it pivot to panels

    Jump

  • Using existing roofs uses no extra space.

  • NSFW

    Nobody is happy with what they have

    Jump

  • Google

    Jump

  • I remember being able to find things much easier, especially when looking for older news articles.

  • I Do Not Recommend Bitwarden

    Jump

  • Enpass works well for me across platforms.

  • Accelerationism

    Jump

  • This is the firing squad for counter revolutionaries.

  • What is your least favourite thing about the fediverse or lemmy?

    Jump
  • Deleted

    Permanently Deleted

    Jump

  • I use Enpass since 1Password became shit. It’s alright.

  • Removed

    Germany unveils strategy for becoming Europe’s strongest military by 2039

    Jump

  • Trek Wars

    Jump

  • Europemaxxing

    Jump

  • Your children will move out faster than you think.

  • Is Starlink A Secret Radar Constellation?

    Jump

  • Sure. The video goes more into detail on this.

  • My experience with local LLM

    Jump

  • That’s your issue.

  • My experience with local LLM

    Jump

  • Do you have 24 GB?

  • Is Starlink A Secret Radar Constellation?

    Jump

  • A satellite constellation is a network of satellites. They aren’t geostationary, but can cover the whole globe because there’s so many of them. When a connection to one drops, it hands off to the next one. GPS and Starlink are examples.

    Radar satellites use radar to image the earth, so called SAR. It can be used to observe the ground even with cloud cover.

    A radar constellation combines this.

  • Qwen3.6 finally makes my Local LlaMa useful

    Jump

  • It’s a tradeoff between RAM and computing power. Discrete GPU RAM is limited. 24 GB is typically the most you can get as a consumer. That means you can‘t run the big models and running several at the same time ca be tricky as well. Offloading from GPU to system RAM is very slow because you run into memory bandwidth between GPU and CPU as the bottleneck.

    As long as the model fits on the GPU, they’re fast. Once you hit the memory limit, it’s game over.

    With unified memory you can run bigger models and also have higher memory bandwidth (depending on CPU).

    Memory bandwidth is super important for running LLMs. That’s also the reason Macs can be good for running LLMs. The M series have unified memory and the Pro, Max, and Ultra Chips have serious high memory bandwidth. An M series Mac with 48 GBs or more is a serious machine for LLMs.

  • How far would you swallow your morals for money?

    Jump

  • Sounds more like you like killing.

  • Deleted

    Permanently Deleted

    Jump

  • Hexbear is actually doing something good for a change.