Quasarke Forums
  • Communities
  • Multi-communities
  • Support Lemmy
  • Search
  • Login
LocalLLaMA@sh.itjust.worksbyShatur@discuss.tchncs.de
16 days

KV Cache Quantization Benchmarks for Long Context

anbeeld.com English
1
    Tests on Qwen 3.6 27B show why TurboQuant is overrated but saved by TCQ, q5 deserves more attention, and symmetric q8 might be a waste of VRAM.
    You must log in or register to comment.

    • pepperfree@sh.itjust.worksEnglish
      10 days

      Is tcq better than kvarn?

      LocalLLaMA@sh.itjust.works

      localllama@sh.itjust.works

      Subscribe from remote instance

      Create post

      Report community

      Modlog
      You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !localllama@sh.itjust.works

      Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

      Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

      As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

      Rules:

      Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

      Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

      Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

      Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

      Visibility: Public

      This community is visible to everyone.

      63 users / Day496 users / Week3.04K users / Month3.06K users / 6 months129 posts1.23K comments1 local subscriber5.6K subscribers
      Mods: MonsterBug@sh.itjust.works
      • BE: 1.0.0-beta.2
      • Modlog
      • Instances
      • Docs
      • Code
      • join-lemmy.org