News for hackers. Stuff that matters.
Re:Why Every AI Model Will Ship as a Torrent by unscaled on Thursday November 12, 2026 @06:00AM (#50465529)
> Movies are different. Search for a movie on a torrent site and you'll see 4K remux, 1080p, 720p [...]. But no one downloads models like this: anyone who wants DeepSeek-V4.1-Flash-1017 wants the same 48 shards.

But this is exactly the situation for AI models as well. If you look for DeepSeek-V4.1-Flash-1017 or Qwen3.8-27B on HuggingFace, you'll see many different releases by various people with different quantizations like FP8, Q4_K_M, INT4, abliterated/uncensored models and various versions that are fined tuned or modded in whichever different way. It feels to me exactly like the various different video encodings.

Yes, there is usually a single, official release from the lab that produced the model (or sometimes a handful of different variants), but very frequently this isn't something you can even run on consumer hardware.

Re:Why Every AI Model Will Ship as a Torrent by _ache_ on Thursday November 12, 2026 @06:52AM (#50465877)
It's useful only for people that actually do the quantisation or research.

End user will never need pirateface.

Re:Why Every AI Model Will Ship as a Torrent by eybarouu on Thursday November 12, 2026 @07:26AM (#50466196)
not true

many end users would suffer if a low parameter count Qwen got taken down from huggingface because of government regulation