@tristanbob: I want my AI to respond faster, so I connected it to @cerebras, who has the fastest inference in the...
I want my AI to respond faster, so I connected it to @cerebras, who has the fastest inference in the industry. Unfortunately, almost all of their models are sold out, and the only one I could pick was Llama 3.1 8B... Which costs $1,500/month! I don't blame Cerebras, but there is no way I'm going to pay that much.