I’m looking at starting a service that involves hosting a lot of LLM models, which are often going to be 16GB+ (compressed). I did a bit of searching for cloud storage providers with cheap egress, and the cheapest I could find is $0.01 per GB, which would still be $0.16+ per download.

How do sites like Huggingface or CivitAI do it? Lots of VC funding?

  • Akisamb@programming.dev
    link
    fedilink
    English
    arrow-up
    6
    ·
    1 year ago

    R2 by cloudfare does not charge egress costs. It’s 0.015$/GB/month for storage. Read operations are 0.36$ per million.

    I do have a hard time believing that they will remain this cheap though, but who knows.

  • Oliver Lowe@lemmy.sdf.org
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    If the files are not going to be changing much, then what is typically done is to use a CDN service (e.g. Cloudflare, Akamai, Fastly). The idea is you have an “origin” which could be any old server which serves your files over HTTP (even a VPS running nginx). The CDN is configured to proxy requests to the origin, building up a cache of the files it serves. The CDN can serve files from cache on their own (very large) infrastructure. See also What is a CDN?

    • minorninth@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      1 year ago

      That’s true, but I just checked a few CDNs and you won’t find one for less than $.01/GB. The lowest I found was $.03/GB.

        • omegastick@lemmy.mlOP
          link
          fedilink
          English
          arrow-up
          1
          ·
          1 year ago

          I was considering this. The hosting provider we use for model training runs doesn’t charge for ingress/egress. Their storage costs would eat us alive though haha. OVH looks much more promising.

  • liori@lemm.ee
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    1 year ago

    Storj does it at 7 USD/TB. And there are providers that technically provide unlimited bandwidth, like Hetzner’s dedicated servers; they still have some abuse limits, but even working within the limits should make it much cheaper. This means custom engineering though.

  • minorninth@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Would BitTorrent be an option?

    There are also ad-supported download sites.

    You could offer users a choice: BitTorrent, ads, or $1 for an instant download.

  • jeff 👨‍💻@programming.dev
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    1 year ago

    Lots of VC funding?

    Probably. They might have gotten additional discounts off of the advertized price by talking with sales and committing to the service for a year or other ways.