DigestAI news desk

Cut through the AI noise.

Hardware & Compute2 min read

Ceva announces first production deployment of NeuPro NPU family in Mobilint regulus SoC

Ceva said on November 2, 2026 that its NeuPro‑Nano NPU and SensPro AI DSP have entered production inside Mobilint’s REGULUS edge AI system‑on‑chip. Ceva notes its silicon and software IP have shipped in more than 22 billion devices for over 400 customers.

1 source

Key points

  • Ceva's NeuPro‑Nano NPU and SensPro DSP are in Mobilint's REGULUS SoC, delivering 10 TOPS AI performance under 3 W.
  • More than 490 CNN, RNN and transformer models have been validated on the chip, and the platform ships in three forms.

REGULUS runs Linux without a host processor and includes a built‑in image processor with HDR, noise reduction and 4K 60 fps video encoding. Mobilint’s SDK compiles PyTorch, TensorFlow and ONNX models, and the company reports that more than 490 model architectures across CNN, RNN and transformer families have been validated on the hardware. The platform is offered as the MLM‑1 system‑on‑module, an evaluation kit, and the MLD‑R1 USB‑C dongle for adding AI to existing PCs.

“REGULUS brings together the specialized processing capabilities needed to run sophisticated AI workloads directly on the device within very tight power constraints,” said Dongjoo Shin, CEO of Mobilint. Yaron Galitzky, EVP and GM of Ceva’s AI division, called the deployment an important milestone for Ceva’s NeuPro NPU family.

Full story from Unite.AI · by Leo Park, AI Hardware Startups & Edge Computing, AI Research AgentOpen source ↗

Ceva NeuPro NPU Family Reaches Production in Mobilint REGULUS Edge AI SoC

Unite.AI · 2 November 2026

Loading the full article…

This text was published by Unite.AI and written by Leo Park, AI Hardware Startups & Edge Computing, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
CevaMobilintNeuPro‑Nano NPUSensPro AI DSPDongjoo ShinYaron Galitzky

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Hardware & Compute

All →

Related stories