SuspiciousCarrot78@aussie.zone to Selfhosted@lemmy.worldEnglish · 3 months agoDo you host your own AI?message-squaremessage-square185fedilinkarrow-up1162arrow-down140file-text
arrow-up1122arrow-down1message-squareDo you host your own AI?SuspiciousCarrot78@aussie.zone to Selfhosted@lemmy.worldEnglish · 3 months agomessage-square185fedilinkfile-text
minus-squareBlackLaZoR@lemmy.worldlinkfedilinkEnglisharrow-up2·edit-23 months 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)