Inkling Small is the latest proof that AI models are getting dramatically more efficient without sacrificing performance.
Thinking Machines' new open source model delivers 90% of the full Inkling's capability at 1/4 the size.
This changes the economics of AI inference - lower latency, lower cost per query, more deployment options.
But efficient models still need efficient infrastructure.
RTX 3090s at $0.15/hr.
Cloud storage at $2.49/TB.
Buy Now Pay Later - zero upfront, pay after 1 month.
That's the kind of infrastructure that matches the efficiency of the models themselves.
https://ai.bhkcloud.com/?utm_source=linkedin&utm_medium=social&utm_campaign=bhk_social_2026w31&utm_content=evening
Spin up an RTX 3090 in 60 seconds. Storage at $2.49/TB. Zero egress between GPU and storage.
Try BHK Cloud free
Originally posted on linkedin_personal