MLD-R1 AI USB
Plug-in on-device USB-type AI accelerator
MLD-R1 AI USB
Plug-in on-device USB-type AI accelerator
MLD-R1 AI USB
Plug-in on-device USB-type AI accelerator
Keep your existing pipeline
Keep your existing pipeline
Keep your existing pipeline
Whether you're deploying a PyTorch model on a Windows laptop or running TensorFlow
inference on an ARM-based industrial PC, MLD-R1 connects and runs.
Whether you’re deploying a PyTorch model on a Windows laptop or running TensorFlow
inference on an ARM-based industrial PC, MLD-R1 connects and runs.
Whether you’re deploying a PyTorch model on a Windows laptop or running TensorFlow
inference on an ARM-based industrial PC, MLD-R1 connects and runs.
AI Frameworks (via SDK qb)
AI Frameworks (via SDK qb)
Keras
Keras
TensorFlow / TensorFlowLite
TensorFlow / TensorFlowLite
PyTorch
PyTorch
ONNX
ONNX
Operating Systems*
Operating Systems*
Windows 11
Windows 11
Linux 22.04.5
Linux 22.04.5
*To be updated
*To be updated
Host Architectures
Host Architectures
x86
x86
ARM
ARM
Powered by the ultra-low-power REGULUS AI SoC
Powered by the ultra-low-power REGULUS AI SoC
~4 W power draw, engineered for 24/7 operation
~4 W power draw, engineered for 24/7 operation
Powered by the ultra-low-power REGULUS AI SoC
~4 W power draw, engineered for 24/7 operation
Turn your device into an
AI inference machine
Turn your device into an
AI inference machine
Turn your device into an
AI inference machine
One stick delivers 10 TOPS (dense, INT8) of on-device AI inference
over a USB port. No chassis swap required.
One stick delivers 10 TOPS (dense, INT8) of on-device AI inference
over a USB port. No chassis swap required.
Accelerate vision to generative AI workload at the edge
Accelerate vision to generative AI workload at the edge
Accelerate vision to generative AI workload at the edge
Mobilint’s NPU architecture has been validated with over
490 open- and closed-sourced models.
Mobilint’s NPU architecture has been validated with over
490 open- and closed-sourced models.
Mobilint’s NPU architecture has been validated with over
490 open- and closed-sourced models.
Specifications
Specifications
Specifications
AI performance
10 TOPS (Dense, INT8)
CPU
Quad-core ARM Cortex-A53, up to 1.2 GHz
Power Consumption
~4 W
Memory
4 GB / 8 GB LPDDR4X at 4,266 MT/s
Supported OS
Windows, Linux
Supported Frameworks
Keras, TensorFlow, TensorFlow Lite, PyTorch, ONNX
LED Indicators
1 (Power LED)
Host Architectures
x86, ARM
Ingress Protection
IP65 (TBD)
Data Interface
USB 3.1 Gen1
Dimensions (mm)
90 ✕ 40 ✕ 16
Weight (g)
88
MLD-R1 goes where MLD-R1 fits
MLD-R1 goes where MLD-R1 fits
MLD-R1 goes where MLD-R1 fits
Forklift Safety
Forklift Safety
Forklift Safety
Real-time pedestrian detection, hard-hat recognition, collision-prevention alerts.
Real-time pedestrian detection, hard-hat recognition, collision-prevention alerts.
AGVs and AMRs
AGVs and AMRs
AGVs and AMRs
Onboard vision and generative AI inference for autonomous mobile robots. Sub-10 W draw compatible with battery-powered operation.
Onboard vision and generative AI inference for autonomous mobile robots. Sub-10 W draw compatible with battery-powered operation.
Construction Machinery
Construction Machinery
Construction Machinery
Restricted-zone intrusion detection and hazard monitoring on moving equipment at construction sites.
Restricted-zone intrusion detection and hazard monitoring on moving equipment at construction sites.
Industrial Safety Monitoring
Industrial Safety Monitoring
Industrial Safety Monitoring
Worker safety monitoring across plants and logistics centers.
Worker safety monitoring across plants and logistics centers.
Speed up model validation and
edge prototyping on your
existing machine, wherever
you are
Speed up model validation and
edge prototyping on your
existing machine, wherever
you are
Speed up model validation and
edge prototyping on your
existing machine, wherever
you are
Run models on portable diagnostic devices without network
connectivity.
Run models on portable diagnostic devices without network
connectivity.
Run models on portable diagnostic devices without network
connectivity.
Have a use case in mind?
Let us know.
Get pricing, evaluation kits and engineering support to start building.
More ways to connect
Technology Partners
Build hardware, software or models that should run with Mobilint NPUs? Join our ecosystem and develop with us.
Become a Partner
Channel Partners
Bring Mobilint products to your market as an authorized reseller or distributor.
Join the Channel
Press & Media
Covering edge AI? Reach our team for interviews, press assets and company news.
Contact Press Team
Something else on your mind?
Contact the team
Have a use case in mind?
Let us know.
Get pricing, evaluation kits and engineering support to start building.
More ways to connect
Technology Partners
Build hardware, software or models that should run with Mobilint NPUs? Join our ecosystem and develop with us.
Become a Partner
Channel Partners
Bring Mobilint products to your market as an authorized reseller or distributor.
Join the Channel
Press & Media
Covering edge AI? Reach our team for interviews, press assets and company news.
Contact Press Team
Something else on your mind?
Contact the team
Have a use case in mind?
Let us know.
Get pricing, evaluation kits and engineering support to start building.
More ways to connect
Technology Partners
Build hardware, software or models that should run with Mobilint NPUs? Join our ecosystem and develop with us.
Become a Partner
Channel Partners
Bring Mobilint products to your market as an authorized reseller or distributor.
Join the Channel
Press & Media
Covering edge AI? Reach our team for interviews, press assets and company news.
Contact Press Team
Something else on your mind?
Contact the team
