RaiderChip’s GenAI NPU Now Supports the Latest Generation of Qwen Models: Qwen3
The record-time integration of Qwen3 reinforces the company’s leadership in the agile deployment of next-generation generative AI models on edge hardware.
Spain, May 7th, 2025
Unveiled just last week, the new Qwen3 AI language model family developed by Chinese company Alibaba Cloud has already been added to RaiderChip’s portfolio of supported models. This swift integration highlights once again the maturity and flexibility of the company’s software stack, which can adapt new models in a smooth and nearly automated way—within timelines that set a true benchmark in terms of agility and time-to-market response.
This capability not only accelerates integration cycles but also ensures that RaiderChip clients can deploy cutting-edge models on edge devices with full autonomy. The result is a hardware platform that combines efficiency, scalability, and immediate response to the latest developments in generative AI.
Qwen3 introduces major innovations, including support for over 100 different languages, along with significant advances in reasoning, instruction-following, and agent capabilities. Thanks to RaiderChip’s GenAI NPU, these features can now be deployed locally across a wide range of applications—from smart homes to security systems—ensuring complete privacy and eliminating the need to rely on cloud services or pay-per-token subscription models.
Download RaiderChip’s GenAI NPU product brief
Companies interested in trying the Generative AI NPU may reach out to RaiderChip for access to our FPGA demo or a consultation on how our IP cores can accelerate their AI workloads.