Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Qwen3-Coder-Next. Parent comment
At 20t/s over 1 month, that's... $19something running literally 24/7. In reality it'd be cheaper than that.
I bet you'd burn more than $20 in electricity with a beefy machine that can run Deepseek.
The economics of batch>1 inference does not go in favor of consumers.
You can run agents in parallel, but yeah, that's a fair comparison.
At 20t/s over 1 month, that's... $19something running literally 24/7. In reality it'd be cheaper than that.
I bet you'd burn more than $20 in electricity with a beefy machine that can run Deepseek.
The economics of batch>1 inference does not go in favor of consumers.