Comment by dimava
1 day ago
Tokens will cost same on Mac and on API because electricity is not free
And you can only generate like $20 of tokens a month
Cloud tokens made on TPU will always be cheaper and waaay faster then anything you can make at home
This generally isn't true. Cloud vendors have to make back the cost of electricity and the cost of the GPUs. If you already bought the Mac for other purposes, also using it for LLM generation means your marginal cost is just the electricity.
Also, vendors need to make a profit! So tack a little extra on as well.
However, you're right that it will be much slower. Even just an 8xH100 can do 100+ tps for GLM-4.7 at FP8; no Mac can get anywhere close to that decode speed. And for long prompts (which are compute constrained) the difference will be even more stark.
A question on the 100+ tps - is this for short prompts? For large contexts that generate a chunk of tokens at context sizes at 120k+, I was seeing 30-50 - and that's with 95% KV cache hit rate. Am wondering if I'm simply doing something wrong here...