LeoMA to Linux and Tech NewsEnglish • 20 hours agoMozilla launches Thunderbolt AI client with focus on self-hosted infrastructurearstechnica.comexternal-linkmessage-square4arrow-up18arrow-down13
arrow-up15arrow-down1external-linkMozilla launches Thunderbolt AI client with focus on self-hosted infrastructurearstechnica.comLeoMA to Linux and Tech NewsEnglish • 20 hours agomessage-square4
minus-square@Bazell@lemmy.ziplinkfedilinkEnglish1•edit-219 hours agoSelf hosted? Not sure that this will be a well working idea assuming how much RAM people have and will have in their systems nowadays.
minus-square@NotSteve_@lemmy.calinkfedilinkEnglish3•17 hours agoYou can actually run simple purpose-built models with very little RAM. I self host immich in a 4GB proxmox VM and it’s able to run its built in image subject recognition AI model without even breaking 50% of that 4GB of RAM
Self hosted? Not sure that this will be a well working idea assuming how much RAM people have and will have in their systems nowadays.
You can actually run simple purpose-built models with very little RAM. I self host immich in a 4GB proxmox VM and it’s able to run its built in image subject recognition AI model without even breaking 50% of that 4GB of RAM