What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Gyrfalcon Technology Inc.’s fourth Lightspeeur AI accelerator was the Lightspeeur 5801, announced on November 14, 2019. The company positioned it for low-power AI inference in edge devices and claimed 2.8 TOPS of performance at 224 mW—an efficiency rating of 12.6 TOPS/W.
What the Lightspeeur 5801 was designed to do
The 5801 was an edge-AI accelerator: a specialized chip intended to run inference—the application of a trained AI model—near the device collecting the data. Its target uses included smartphones, smart cameras, surveillance systems, IoT endpoints and other consumer electronics. It was not presented as a general-purpose CPU replacement.
Gyrfalcon based the chip on its Matrix Processing Engine and processing-in-memory approach. EE Times reported that it contained about 28,000 processing nodes and 10 MB of memory, and was primarily optimized for convolutional neural networks (CNNs), which are commonly used for image-recognition tasks.
How fast and power-efficient was it?
Gyrfalcon’s 2019 launch figures were 2.8 TOPS at 224 mW, equivalent to the company’s headline rating of 12.6 TOPS/W. TOPS means trillions of operations per second; TOPS/W expresses throughput relative to power consumption. The company also claimed latency under 4 ms, but the launch coverage did not specify the workload or test conditions for that figure.
#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
In a 2020 technical white paper, Gyrfalcon again gave 12.6 TOPS/W and also cited 468 frames per second per watt with power under 250 mW. Those are company-reported figures, not a directly comparable independent benchmark. EE Times reported a variable clock range of 50–200 MHz, a 6 × 6 mm package and support for 448 × 448 image input.
Where the chip was used
EE Times reported that LG had designed the 5801 into its Q70 smartphone for camera effects, including Bokeh. This was a reported design-in for a specific phone, not evidence that the accelerator was used across LG’s wider product range.
Rank #2
- High-Performance Dual-Core with Ample Memory--- Equipped with a 360MHz dual-core RISC-V processor, 32MB of onboard PSRAM, and 32MB of Flash memory, providing powerful processing capabilities and ample runtime for complex multimedia applications and edge computing.
- Powerful Multimedia Processing Center--- Integrated with a dedicated image processor (ISP), H.264 video encoder, and JPEG codec, perfectly supporting camera input and video processing, making it an ideal choice for developing smart displays, video surveillance, and other projects.
- Hardware-Level Security Protection--- Built-in digital signature, encryption accelerator, and key management unit, providing a one-stop hardware-level security solution from secure boot and data encryption to access control management, ensuring the security of your products and data.
- Full Connectivity Coverage: Wi-Fi 6, Bluetooth, PoE Power Supply--- Onboard with an ESP32-C6 chip, supporting the latest Wi-Fi 6 and Bluetooth 5.0; it also integrates an Ethernet port with PoE functionality, providing high-speed, flexible, and stable network connectivity, and can be powered directly via Ethernet cable, simplifying deployment.
- Rich interfaces and strong expandability--- It provides a MIPI camera/display interface, high-speed USB, SD card slot, microphone/speaker interface and a large number of programmable GPIOs, which greatly facilitates the expansion of external devices and meets the needs of various human-computer interaction and Internet of Things applications. Supports AI Speech Interaction: Allows access to online large model platforms such as ChatGPT, DeepSeek, Doubao, etc.
The chip’s processing approach could also handle some natural-language workloads by converting audio into an RGB-image representation. That is a specialized way of presenting audio data to the processor, not an indication that the 5801 was a general-purpose speech or language processor.
What developers could evaluate
EE Times reported an available development kit called the 5801 Plai Plug. It supported ResNet, MobileNet and VGG16, with TensorFlow, PyTorch and Caffe listed as supported frameworks. Gyrfalcon also described USB 3.0 accelerator dongles for Windows and Linux PCs, as well as evaluation with Raspberry Pi.
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Fix the driver behind crashes, sound loss and screen glitches3Repair Windows errors before they cause bigger problemsRank #3
- Powered by 26 Tera-Operations Per Second (TOPS) Hailo-8 AI Processor.
- 2.5W typical power consumption
- 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.
These reports establish that a development kit and evaluation options existed at the time. They do not establish whether a kit is currently available to buy; check with Gyrfalcon or a distributor for present-day stock and support.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.How it fit into Gyrfalcon’s chip lineup
Gyrfalcon’s own portfolio figures provide context for the company’s efficiency claims. The 5801’s 12.6 TOPS/W sat between the portfolio’s listed figures for the 2801S and 2803S. Those figures describe efficiency, not a full ranking of real-world speed: no comparable throughput, workload or test conditions are stated for all three chips.
Rank #4
- 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.
| Chip | Listed efficiency | Qualification |
|---|---|---|
| Lightspeeur 2801S | 9.3 TOPS/W | Listed in Gyrfalcon’s portfolio; date and test conditions not stated. |
| Lightspeeur 5801 | 12.6 TOPS/W | Gyrfalcon’s 2019 claim, repeated in its 2020 technical white paper. |
| Lightspeeur 2803S | 24 TOPS/W | Listed in Gyrfalcon’s portfolio for higher-throughput applications; date and test conditions not stated. |
Marc Naddell, Gyrfalcon’s vice president of marketing, summed up the company’s pitch as a balance of performance, energy efficiency and cost. EE Times reported a starting price of about $5 in 2019; that historical reported price should not be treated as a current retail price.
Quick Recap
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.
