Comment by bel8
4 months ago
But it's quantized right? It's not the same almost-free DeepSeek you get from the API.
And once the context gets large, it slows down.
"up to" 150, is doing a lot of work there.
4 months ago
But it's quantized right? It's not the same almost-free DeepSeek you get from the API.
And once the context gets large, it slows down.
"up to" 150, is doing a lot of work there.
Yes, it's quantized (4 bit). Sure, it's... not quite as good as what's on offer via API. And sure, "up to" does a lot of work (I don't have an average/median for you but it feels fast to me).
But it's usable, fully local, fully private, and has no subscriptions and no operating costs other than electricity.