RaiderChip’s Edge NPU reaches more than 50 Generative AI Models with the addition of Qwen3.8-27B
The new milestone demonstrates the hardware architecture’s ability to support new generations of AI models without requiring silicon redesign.
Vendor:
RaiderChip
Category:
NPU
NPU IP core
The GenAI NPU IP Core brings Generative AI inference directly to AMD Adaptive SoCs.
Overview
The GenAI IP is the smallest version of our NPU, tailored to small devices such as FPGAs and Adaptive SoCs, where the maximum Frequency is limited (<=250 MHz) and Memory Bandwidth is lower (<=100 GB/s).
GenAI Inference on Adaptive SoC
The GenAI NPU IP Core brings Generative AI inference directly to AMD Adaptive SoCs.
Deploy state-of-the-art LLMs and VLMs locally, right from HuggingFace, with complete control over data, performance and cost.
No cloud dependency. No third-party APIs. No variable fees.
Artificial Intelligence running on your AMD Versal devices:
- Fully Offline
- Standalone
AI Models. Freedom to Choose.
Add vision, language, reasoning and voice to your devices.
Edge AI beyond GPUs.
Higher Performance per Watt
The GenAI NPU IP Core running on AMD Versal surpasses GPU-based platforms, like Nvidia Jetson Orin (Super mode):
- Up to +110% higher raw throughput
- Up to +63% higher energy efficiency
- Up to +140% better Energy Delay Product (EDP)
RaiderChip NPU redefines energy efficiency.
Next-gen Artificial Intelligence locally
Protect critical data and operations by running fully on premises your AI workloads. No cloud transfers, no third-party access — full control of your infrastructure and information.
Operate independently in remote environments without requiring network connectivity.
Run cutting-edge open models locally. No variable subscriptions to third parties, no API fees.
Precision From Q4 to FP32
FP32 precision to deliver maximum intelligence to run raw AI models natively. Or 4-bit and 5-bit Quantization for a speed boost.
Try our Generative AI Accelerator Demo
Everything provided to boot your board and turn it into a standalone GenAI accelerator on your premises.
Download AI models from HuggingFace, or run your own, natively on your site.
- Chat with Vision, Reasoning, Language models
- Evaluate latency, throughput, and intelligence
Post-trained and fine-tuned models are supported natively without sharing your proprietary weights.
Your model. Your weights. Your control.
Performance & Resource Usage
Select the device that best fits your performance, power, and cost requirements, we take care of the rest!
Block Diagram
Click to open fullscreen
1 /
4
Specifications
Identity
Part Number
GenAI IP
Vendor
RaiderChip
Type
Silicon IP
Application
Edge AI
Videos
AMD presenting RaiderChip GenAI NPU Edge LLM demo
AMD presenting RaiderChip GenAI NPU Edge LLM demo in its booth at ISE 2025 (video by Charbax)
Files
Note: some files may require an NDA depending on provider policy.
Provider
HQ:
Spain
Learn more about NPU IP core
RaiderChip Unites Generative AI and Autonomous Robot Control on a single NPU
The new demonstrator enables intent-based voice control of Unitree robots in a virtual replica environment, combining robot policies and Generative AI models running concurrently on its NPU.
RaiderChip showcases the evolution of its local Generative AI processor at ISE 2026
At ISE 2026, RaiderChip showcased the evolution of its local Generative AI processor (NPU), ready for integration into SoCs and ASICs, enabling visitors to interact with up to 18 different models, including both LLMs and multimodal models, all running locally on device.
RaiderChip NPU leads edge LLM benchmarks against GPUs and CPUs in academic research paper
The startup’s NPU surpasses NVIDIA’s Jetson Orin, the company’s flagship edge platform, in both raw performance and energy efficiency.
RaiderChip NPU for LLM at the Edge supports DeepSeek-R1 reasoning models
The rise of optimized reasoning models, capable of matching the performance of massive solutions like ChatGPT, strengthens RaiderChip’s commitment to AI acceleration through its affordable and high-performance edge devices.
RaiderChip unveils its fully Hardware-Based Generative AI Accelerator: The GenAI NPU
RaiderChip has officially launched the GenAI NPU, a fully hardware-based accelerator that sets new standards for efficiency and scalability in Generative AI. The GenAI NPU retains the key features of its predecessor, the GenAI v1: offline operation and autonomous functionality.
Frequently asked questions about NPU IP cores
What is NPU IP core?
NPU IP core is a NPU IP core from RaiderChip listed on Semi IP Hub.
How should engineers evaluate this NPU?
Engineers should review the overview, key features, supported foundries and nodes, maturity, deliverables, and provider information before shortlisting this NPU IP.
Can this semiconductor IP be compared with similar products?
Yes. Buyers can compare this product with similar semiconductor IP cores or IP families based on category, provider, process options, and structured technical specifications.