Skip to main content
SiliconANGLE· Duncan Riley·· 1 hours agoAI Score42

SiMa.ai Palette 3.0 Runs Multiple AI Models on One Chip, Boosts Throughput Up to 3.5x

SiMa.ai’s Palette 3.0 runs many AI models on one chip and lifts throughput up to 3.5 times

AI Overview

SiMa.ai released Palette 3.0, a software suite that runs multiple AI models concurrently on its Modalix MLSoC and lifts throughput up to 3.5x. The release adds speculative decoding via EAGLE3, DFlash and Gemma 4 MTP, plus support for large MoE models such as GPT-OSS-20B on the 16GB system-on-module. Open-source code is available on GitHub.

Source:SiliconANGLE · siliconangle.com

Subscribe to the newsletters

Free, by email. No account needed. Pick one or both.

No spam. Unsubscribe anytime by emailing team@midu.si. Want alerts and full data? Sign up free (separate from the newsletter). Privacy.

Not investment advice. Midu summarizes public reports and SEC filings for information only. · Free API · Pricing