Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
LG AI Research adopted FuriosaAI’s RNGD inference accelerator for running EXAONE models, and the companies said they would offer RNGD servers to enterprise customers. The July 2025 announcement describes an enterprise adoption and planned supply relationship—not an LG-wide purchasing commitment—and does not disclose contract value, order volume, or pricing.
What the FuriosaAI–LG deal covers
On July 22, 2025, FuriosaAI announced that LG AI Research had selected its RNGD accelerator, pronounced “Renegade,” for EXAONE inference after evaluating performance, energy efficiency, and the software stack. FuriosaAI said the companies would offer RNGD Server to enterprises using EXAONE, including customers in electronics, finance, telecommunications, and biotechnology. FuriosaAI’s announcement names LG AI Research; it does not establish that every LG business committed to buy the systems.
The named product is enterprise server infrastructure, not a consumer AI chip or retail computer. The announcement does not provide order quantities, contract value, per-system pricing, deployment counts, or purchase terms.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minutePC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11What the reported performance figures mean
FuriosaAI says LG AI Research evaluated EXAONE 3.5 models with 7.8 billion and 32 billion parameters, using 4K and 32K context windows. In that evaluation, RNGD delivered 2.25× better LLM inference performance per watt than the GPU-based solution used for comparison, according to the vendor. This is a company-reported result tied to the described evaluation, not an independently replicated or universal comparison between RNGD and GPUs. The announcement does not provide enough detail to reproduce the headline comparison independently. FuriosaAI’s reported evaluation
#1 Best Overall
- ✅Powered by 26 Tera-Operations Per Second (TOPS) Hailo-8 AI Processor. 2.5W typical power consumption
- ✅Scalable, enabling simultaneous processing of multi-streams & multi-models
- ✅Enabling real-time, low latency and high-efficiency AI inferencing on the edge devices
- ✅Supports TensorFlow, TensorFlow Lite, ONNX, Keras, Pytorch frameworks
- ✅Supports Linux and Windows. Supports the temperature range of -40°C to 85°C
The same announcement gives selected throughput figures for EXAONE 3.5 32B running at batch size one on one server with four RNGD cards:
| Context window | Reported throughput | Configuration and attribution |
|---|---|---|
| 4K | 60 tokens per second | One server with four RNGD cards, batch size one; reported by FuriosaAI in 2025. |
| 32K | 50 tokens per second | One server with four RNGD cards, batch size one; reported by FuriosaAI in 2025. |
FuriosaAI describes an RNGD Server as eight accelerators in an air-cooled 4U chassis. That is the server description, distinct from the four-card configuration cited for the throughput figures. The announcement’s performance details
Rank #2
- High-Performance AI Processing: The MX3 is designed to handle the most demanding AI computer vision workloads, delivering exceptional performance and efficiency.
- Flexible Integration: The MX3 can be easily integrated into your existing systems via its M.2 M-key form factor and support for Linux operating systems.
- Energy Efficient: The MX3 is designed to provide high performance while minimizing power consumption.
- Comprehensive Software Development Kit (SDK): The MX3 is supported by a comprehensive SDK that simplifies development and deployment.
- Hardware compatability: The MX3 is compatible with the PCI-SIG M.2 M-key 2280 Specification. It can be used with the Raspberry Pi 5 with a M-key 2280 HAT.
How LG AI Research described its choice
Kijeong Jeon, Lead, Product Unit, LG AI Research, said in FuriosaAI’s July 22, 2025 announcement: “After extensively testing a wide range of options, we found RNGD to be a highly effective solution for deploying EXAONE models. RNGD provides a compelling combination of benefits: excellent real-world performance, a dramatic reduction in our total cost of ownership, and a surprisingly straightforward integration,”
This is a statement from an LG AI Research representative quoted in FuriosaAI’s announcement, rather than an independent analyst assessment. Source and context for the quote
What changed with the LG U+ appliance in 2026
In March 2026, FuriosaAI said it and LG U+ had launched a Sovereign AI Appliance integrating an RNGD accelerator, LG’s EXAONE 4.0 model, and the ixi-Enterprise platform in one server package. FuriosaAI claimed 30% lower total cost of ownership than traditional GPU clusters; that is the vendor’s claim, separate from the 2025 performance-per-watt result, and is not independently verified in the cited material. FuriosaAI’s March 2026 announcement
LG U+’s March 9 newsroom post describes a March 4 agreement as an MOU to develop the appliance. It says the system is designed to process data on-premises instead of sending it to an external cloud, combining LG U+’s enterprise platform, EXAONE 4.0, and FuriosaAI’s NPU. The post also outlines possible future cooperation in NPU-as-a-Service and physical AI. FuriosaAI calls the product launched, while LG U+ describes an MOU to develop it; the available announcements therefore do not establish general commercial availability or order terms. LG U+’s March 9, 2026 newsroom post
Rank #4
- ✅Powered by 26 Tera-Operations Per Second (TOPS) Hailo-8 AI Processor. 2.5W typical power consumption
- ✅Scalable, enabling simultaneous processing of multi-streams & multi-models
- ✅Enabling real-time, low latency and high-efficiency AI inferencing on the edge devices
- ✅Supports TensorFlow, TensorFlow Lite, ONNX, Keras, Pytorch frameworks
- ✅Supports Linux and Windows. Supports the temperature range of -40°C to 85°C
What to compare before choosing an inference accelerator
The reported figures are not enough by themselves to determine whether RNGD is a better fit than a GPU system for a particular deployment. A useful comparison needs equivalent workloads and operating targets, including:
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
- Model, precision, and software support.
- Batch size, input and context length, and latency target.
- Tokens per second and performance per watt under that workload.
- Accelerator and server configuration, rack power, and cooling requirements.
- Total cost for the same workload, including the infrastructure needed to run it.
Neither the July 2025 announcement nor the March 2026 appliance statements establish a like-for-like independent benchmark, system price, or customer-specific deployment result. The published performance and cost comparisons should therefore be read as vendor-reported claims, not as proof that RNGD is categorically faster or cheaper than GPUs.
Quick Recap
Best Value
- DEEPX DX-M1M NPU: Powered by the DEEPX DX-M1M neural processing unit, purpose-built for efficient on-device AI inference workloads.
- COMPACT M.2 2242 FORM FACTOR: Fits the standard M.2 2242 slot, making it easy to integrate into embedded systems, edge devices, and compact computing platforms.
- EDGE AI ACCELERATION: Designed to accelerate deep learning inference at the edge, enabling real-time AI applications without relying on cloud connectivity.
- RADXA AICORE MODULE: The Radxa AICore DX-M1M delivers a plug-and-play AI compute solution ideal for robotics, smart cameras, and industrial automation.
- WARRANTY AND ORIGIN: Backed by a 1-year manufacturer warranty and crafted with quality components for reliable long-term performance in demanding environments.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
