I have 8gb VRAM and use local LLM for Ai. xD Thanks to Vulkan it partially runs on GPU and partially on CPU, so its not too slow running “bigger” models.
And no, before anyone downvotes me, I am not an Ai bro. I do not generate everything with Ai (would be difficult with low end hardware anyway).
Yeah it’s certainly not too small for professional applications that don’t require huge amounts of power. If it’s cheap enough at the time I might look at this for my next build.
I have 8gb VRAM and use local LLM for Ai. xD Thanks to Vulkan it partially runs on GPU and partially on CPU, so its not too slow running “bigger” models.
And no, before anyone downvotes me, I am not an Ai bro. I do not generate everything with Ai (would be difficult with low end hardware anyway).
Yeah it’s certainly not too small for professional applications that don’t require huge amounts of power. If it’s cheap enough at the time I might look at this for my next build.