SWE-2 Flash is based on @thinkymachines Inkling-Small, an American model with 276B total and 12B active parameters. The small size, combined with our highly optimized inference stack allows us to offer it at a 5x lower cost and 3x higher speed than SWE-2.
Cognition's SWE-2 Flash is based on Thinking Machines' Inkling-Small model
AICognition says SWE-2 Flash is built on Thinking Machines' Inkling-Small, an American model with 276B total and 12B active parameters. Cognition says its inference stack lets it offer SWE-2 Flash at 5x lower cost and 3x higher speed than SWE-2.
Source details
Cognition · x.comPublished · added here
Original title: SWE-2 Flash is based on @thinkymachines Inkling-Small, an American model with 276B total and 12B active parameters. The small size, combi...