Stamets@lemmy.world to People Twitter@sh.itjust.works · 2 years agoThe dreamlemmy.worldimagemessage-square238linkfedilinkarrow-up11.98Karrow-down143
arrow-up11.94Karrow-down1imageThe dreamlemmy.worldStamets@lemmy.world to People Twitter@sh.itjust.works · 2 years agomessage-square238linkfedilink
minus-squareCeeBee@lemmy.worldlinkfedilinkarrow-up2·2 years ago I don’t know of an LLM that works decently on personal hardware Ollama with ollama-webui. Models like solar-10.7b and mistral-7b work nicely on local hardware. Solar 10.7b should work well on a card with 8GB of vram.
minus-squareParetoOptimalDev@lemmy.todaylinkfedilinkarrow-up1·2 years agoIf you have really low specs use the recently open sourced Microsoft Phi model.
Ollama with ollama-webui. Models like solar-10.7b and mistral-7b work nicely on local hardware. Solar 10.7b should work well on a card with 8GB of vram.
If you have really low specs use the recently open sourced Microsoft Phi model.