Thank you. We've already seen what the future looks like, and it's models on a chip. It's several orders of magnitude faster at inference than anything else:
AMD acquired this company, and I hope they start releasing consumer hardware based on their tech.
Your move Intel and NVIDIA, give us what we want and stop hording GPUs in data centers.
Intel and NVIDIA aren't hoarding GPUs in data centers. You can buy them if you have money, but billionaires are hoarding money.
For the record, "the future" you are describing is running a tiny LLM from 2 years ago.
Those on-device weights are horribly outdated, underperform for their size, and cannot be updated to use a different model. I don't think Nvidia is afraid of Taalas.