[henry2023]

local models are 3 to 6 months behind SOTA models with the huge benefit of not needing to send all your IP to a shady third party.

If inference cost comes down (as it has been for the last few years) you’ll be able to run today’s SOTA in your laptop by the end of the year.

[ghrl]

I would say that is highly unlikely if by SOTA models you are not just referring to coding benchmarks but more general purpose ability and domain-specific knowledge. For example Kimi 2.6, which is comparable to Opus 4.6, is roughly 500+GB large, and I don't see how that would run on consumer hardware anytime soon. Besides, this is not just about the technical feasibility, but also economically not viable whatsoever. Why should consumer laptops be capable of running such models, when they would be massively underutilized most of the time, when inference providers can produce the same results faster, cheaper and a lot more viable economically?

[henry2023]

Because privacy has perceived value.

[sourcecodeplz]

It runs right now on 512gb RAM Macs and PCs.

[Our_Benefactors]

It runs like shit though in terms of tokens/second and still has a reduced context window. Vs a single claude prompt can easily get into 300k tokens without breaking a sweat.

I want local AI to be a thing but the hardware isn’t here yet, because the only options are a Mac Studio or DGX machines strapped together. RAM prices needs to crash before local AI has a chance at actually competing.

[zozbot234]

The more recent Chinese models are no longer heavily limited by context size. It can easily fit in RAM on a prosumer laptop. (You can also use swap space to extemd that, since context is only written to once per inference, thus a relatively mild wear-and-tear concern.)

[Our_Benefactors]

Claude has 1M context window for the enterprise. 128k feels like a toy in comparison.

[sourcecodeplz]

Deepseek pro/flash both have 1m.

[ATMLOTTOBEER]

You’re right, and it feels like these people saying otherwise either don’t use these tools professionally (and therefore can’t tell a difference between local/cloud models) or literally just haven’t tried running local models

As soon as I can buy hardware for less than 5k that runs an opus 4.6+/5.5 model locally I will do it instantly

[fg137]

"shady third party"

If Claude hosted on AWS bedrock is not considered trustworthy, I have some bad news for you.

[henry2023]

Anthropic illegally downloaded virtually all copyrighted material in the world to train their models. What makes you think they will have even a little consideration for your IP?

[fg137]

Let's say as a matter of fact that Anthropic seizes every opportunity to steal IP.

How is that going to work on Bedrock, when they don't even manage the infrastructure?

[linkregister]

*tortiously downloaded

[lurking_swe]

the bigger issue is context windows. HUGE difference there.