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.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.