Sabitlenmiş Tweet
Flying Ginsu
1.2K posts

Flying Ginsu
@FlyingGinsu
Deploying Diffusion Models on Azure and AWS • Generative AI Infrastructure
Neptune Katılım Ağustos 2023
510 Takip Edilen918 Takipçiler
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi

> been paying $200/month for cloud AI APIs
> laptop: M2 MacBook, 16GB RAM
> tried running models locally, garbage quality after 4K tokens
> read this TurboQuant breakdown on Tuesday
> applied 3-bit KV cache compression
> same MacBook now runs 100K token conversations
> quality: identical to cloud
> cancelled all API subscriptions Wednesday
> it's been 3 days
> saved $200/month forever
> with a free algorithm from a free paper
> my MacBook didn't change. the math did
BuBBliK@k1rallik
English
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi
Flying Ginsu retweetledi




































