{"id":50320747,"user":"spwa4","time":1793484626,"time_ago":"17 hours ago","type":"comment","content":"

Best model on 2xSpark currently is GLM 5.3 flash ... but really does require 2x Spark. 25 to 60 tok/s with MTP.","comments":[{"id":50322547,"user":"anakaine","time":1793505125,"time_ago":"11 hours ago","type":"comment","content":"

2x Spark? As in two DGX Spark machines? That is obscenely expensive.","comments":[{"id":50323388,"user":"cyberpunk","time":1793517909,"time_ago":"8 hours ago","type":"comment","content":"

Is it? How much would it cost to hire a person to do the same work two of these can do?","comments":[{"id":50324277,"user":"hamdouni","time":1793528996,"time_ago":"5 hours ago","type":"comment","content":"

Maybe fair to compare to using AI subscription ~20$/m (not Anthropic neither Openai)","comments":[{"id":50324342,"user":"spwa4","time":1793529607,"time_ago":"4 hours ago","type":"comment","content":"

Especially now with OpenAI constantly changing (and always reducing) what the subscription can do ... At least it will keep working.

Right now I need 4 subscriptions to do what 1 used to do. And they're tightening it further, without announcing:

https://news.ycombinator.com/item?id=50320588

(technically it isn't even legal, since changing what people get after they've agreed to the sale is obviously highly illegal)

Not that they've ever actually announced how much a subscription buys you. In fact the token use for a task on the API is also not consistent, so even on the API you don't know. And then there's Sam Altman in interviews, where he says what he wants to do: you submit a prompt, ChatGPT sends you a price and just charges it.","comments":[],"comments_count":0,"level":3,"url":"item?id=50324342"}],"comments_count":1,"level":2,"url":"item?id=50324277"}],"comments_count":2,"level":1,"url":"item?id=50323388"}],"comments_count":3,"level":0,"url":"item?id=50322547"}],"comments_count":4,"url":"item?id=50320747"}

Comment by spwa4