# Cognition's SWE-2 Flash is based on Thinking Machines' Inkling-Small model

> 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...

- Source: Cognition
- Published: 2026-11-04T19:55:23.000Z
- Bad Influence: https://badinfluence.news/items/qomna0mjydp23pf36mvp16ocp
- Original: https://x.com/cognition/status/2118069618749415821

## Summary

Cognition 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.

## Post

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.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Ftweet_video_thumb%2FHWTio9DXwAAa6yA.jpg&mode=thumb&exp=1794009600&sig=13810f2e18f8a133)