ainewsblitz.com

Breaking

Cactus Compute Releases Gemma 4 E2B Hybrid Model That Routes Hard Prompts to the Cloud Using Confidence Scores

Cactus Compute Releases Gemma 4 E2B Hybrid Model That Routes Hard Prompts to the Cloud Using Confidence Scores
  • Foundation Models
  • Open Source
  • Infra & Chips

Cactus Compute has post-trained Google's compact Gemma 4 E2B model so that it emits a per-response confidence score, letting a device handle prompts locally when it is sure of its answer and hand off harder ones to a larger cloud model. The release, published under an MIT license (subject to Gemma's terms of use) on GitHub and Hugging Face, tackles one of the thorniest problems in hybrid inference: knowing when a small on-device model is likely to be wrong.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year