Serving barely useful GLM 5.2 costs what? $15k? Actually useful is like $50k? You’ll never recoup the cost unless you ‘locally’ means ‘inference provider is not the model provider’?
I bought my spark and the models have already improved in that time (qwen3.6, speculative decoding 2x tgen, diffusion gemma 4x tgen) and I expect this to improve. Look out another 2-3 years, local is going to be very competitive.
This website is so out of touch with reality.
When a low speed of the order of one token per second is accepted, any open weights LLM can be run on an ordinary PC (with the weights read from SSDs) and the cost becomes negligible.
Such a low speed would be annoying for a chat, but I do not believe that it is "barely useful" for a coding assistant. There are plenty of tasks for which it is fine to get results some hours later or even overnight, and batching multiple tasks can complete them in about the same time as a single task.
So maybe for a hobby project this is fine, but for something you have to take to market and compete with... I think it'd be a really rough sell.
EDIT: also, just to be clear: if there was a practical path to using local AI, I'd take it in a heartbeat. I hope it gets to the point that it's better to use local than paying someone $200/mo. But right now, that $200/mo is the clear best option. I get making compromises for ideology but the compromises are too big for me right now.
You don't need to have it always on? This is a far cry from "$200/month," but I do not think it's $50k for "useful." Do you see it differently?
100/s*month*(.14/million) = $37
A decent deal but Flash is quite dumb and you still have to pay for output tokens