K3 and other open source models are obviously insanely bullish for compute and RAM. Inference was always going to be almost all high performance compute usage. More people that can do inference = more demand.
Open source models like K3 are bullish for compute and RAM demand as more inference drives usage.
K3 and other open source models are obviously insanely bullish for compute and RAM. Inference was always going to be almost all high performance compute usage. More people that can do inference = more demand.
K3 and other open source models are obviously insanely bullish for compute and RAM. Inference was always going to be almost all high performance compute usage. More people that can do inference = more demand.
The story of AI in the next few years is going to be compute: an essay on the future of AI. K3 in 2 days is already #10 on OpenRouter with ~140B tok/day, and it’s infra is crumbling. Throughput is down from 30tok/s to 13tok/s, E2E latency is up to 72s and time to first token is >20s! It would cost
Bullish on whoever provides inference