SuspiciousCarrot78@aussie.zone to Selfhosted@lemmy.worldEnglish · 2 days agoDo you host your own AI?message-squaremessage-square199linkfedilinkarrow-up1174arrow-down139file-text
arrow-up1135arrow-down1message-squareDo you host your own AI?SuspiciousCarrot78@aussie.zone to Selfhosted@lemmy.worldEnglish · 2 days agomessage-square199linkfedilinkfile-text
minus-squareBlackLaZoR@lemmy.worldlinkfedilinkEnglisharrow-up2·edit-216 hours agoI use LMStudio, because it has quality of life improvements like nice GUI and huggingface search engine. Also they have Vulkan backend that at least on 7900XTX is ~10% faster than rocm (on LLama 3 8b Q4_0 it gets 115Tokens/s vs 105 on rocm)
I use LMStudio, because it has quality of life improvements like nice GUI and huggingface search engine. Also they have Vulkan backend that at least on 7900XTX is ~10% faster than rocm (on LLama 3 8b Q4_0 it gets 115Tokens/s vs 105 on rocm)