AWS / update detail

Gemma-4-31B-it-assistant and Gemma-4-31B-IT-NVFP4 models now available on Amazon SageMaker JumpStart

Official AWS changelog summary with source attribution, release tags, and community reactions.

Track this AWS release note alongside related changelog updates, risky changes, and weekly digest signals from the developer community.

AWS·Sep 14, 2026, 05:32 PMFeatureAI-assisted summary

Summary

Gemma-4-31B-it-assistant and Gemma-4-31B-IT-NVFP4 models are now available on Amazon SageMaker JumpStart for easy deployment.
The assistant‑tuned variant supports multimodal inputs (text, images, video frames), a 256K‑token context window, 140+ languages, hybrid attention and native function calling for autonomous agents.
The FP4‑quantized variant reduces memory to ~18.5 GB (68% smaller) and delivers ~2.5× faster inference while retaining 97‑99% of the original model quality.

featuresource healthy

Official source Last checked Sep 20, 2026, 3:04 PM

Loading follow options…

official source

Verify the original release note

Every summary should remain traceable to the original changelog or release source.

AI-assisted summarysource healthyLast checked Sep 20, 2026, 3:04 PM

related channels

Turn this AWS release note into a weekly digest for the tools you actually use.