Toybrick RK3399Pro AI Developer Kit -6G+32GB eMMC Base
Rated 3.5/5 based on 11 customer reviews

Toybrick RK3399Pro AI Developer Kit -6G+32GB eMMC Base

Available: Out of Stock
Wishlist
$427.99 $556.99
Successful pre-order.Thanks for contacting us!
The TB-RK3399Pro development board is equipped with the super-performance AI processor RK3399Pro, which has superior general-purpose computing performance. It equips ARM big.LITTLE architecture, dual-core Cortex-A72 + quad-core Cortex-A53, with technical leadership in overall performance and power consumption; quad-core ARM high-end GPU Mali-T860, integrates multiple bandwidth compression technology, providing overall excellent performance. Its on-chip NPU (Neural Network Processor) offers up to 3.0TOPs computing power.
The TB-RK3399Pro development board has rich external interfaces, including 4 lanes PCIE and Mini PCIE, dual high-speed USB3.0 port Type-C + USB3.0 Type-A, dual MIPI CSI and dual ISP with pixel processing capability up to 1300W pixels, and HDMI2.1, DP1.2, MIPI-DSI and EDP; it also supports 8-channel digital microphone array input.
On the software side, TB-RK3399Pro is pre-installed Android and Linux system, support dual system boot and one-button OS switching. integrated rich AI application development components, providing friendly and concise application programming interface, seamless docking NPU to achieve AI computing hardware acceleration, support Various model inferences such as TensorFlow/TensorFlow lite/Caffe.
Specification
SoC Rockchip RK3399Pro (NPU built-in)
NPU Support 8-bit/16-bit Inference
Deep Learning Support TensorFlow/Caffe Model
CPU Dual Cortex-A72 +Quad Cortex-A53,64-bit CPU
Frequency up to 1.8GHz
GPU Mali-T860MP4 GPU
Memory 6GB LPDDR3
EMMC 32GB eMMC
Support SIM Card, TF Card
USB 2 x USB 2.0 Host, 1 x USB 3.0 Host, 1 x USB 3.0 Type-C
Dual OS Android 8.0 & Fedora 28
RK3399Pro
Dual-core Cortex-A72 up to 1.8GHz; Quad-core Cortex-A53 up to 1.4GHz
NPU up to 3.0TOPS
Mali-T860MP4 GPU
Dual-channel DDR3/DDR3L/LPDDR3/LPDDR4
4K UHD H265/H264/VP9
HDR10/HLG
H264 encoder
Dual MIPI CSI and ISP
USB Type-C and USB 2.0
CPU Big.Little architecture: Dual Cortex-A72 + Quad Cortex-A53, 64-bit CPU
Frequency is up to 1.8GHz
NPU Support 8-bit/16-bit Inference
Support TensorFlow/Caffe Model
GPU Mali-T860MP4 GPU, OpenGL ES1.1/2.0/3.0/3.1, OpenVG1.1, OpenCL, DX11
Supports AFBC (ARM Frame Buffer Compression)
Memory 3GB/6GB LPDDR3
Support eMMC 5.1 with HS400, SDIO 3.0 with HS200
Multi-Media 4K VP9 and 4K 10bits H265/H264 video decoders, up to 60fps
1080P other video decoders (VC-1, MPEG-1/2/4, VP8)
1080P video encoders for H.264 and VP8
Video post processor: de-interlace, de-noise, enhancement for edge/detail/color
Display Dual VOP: one supports 4096x2160 with AFBC supported; the other supports 2560x1600
Dual channel MIPI-DSI (4 lanes per channel)
eDP 1.3 (4 lanes with 10.8Gbps) to support display, with PSR
HDMI 2.0 for 4K 60Hz with HDCP 1.4/2.2
DisplayPort 1.2 (4 lanes, up to 4K 60Hz)
Supports Rec.2020 and conversion to Rec.709
Interface Dual 13M ISP and dual channel MIPI CSI-2 receive interface
USB 3.0 with type-C supported
PCIe 2.1 (4 full-duplex lanes)
Embedded low power MCU for other application
8 channels I2S supports 8 channels RX or 8 channels TX
Shipping list:
1 x TB-RK3399Pro development board with Heatsink (6G+32G eMMC)
1 x Acrylic case with screws
1 x 12V-2A power supply
1 x Type C cable
The TB-RK3399Pro development board is equipped with the super-performance AI processor RK3399Pro, which has superior general-purpose computing performance. It equips ARM big.LITTLE architecture, dual-core Cortex-A72 + quad-core Cortex-A53, with technical leadership in overall performance and power consumption; quad-core ARM high-end GPU Mali-T860, integrates multiple bandwidth compression technology, providing overall excellent performance. Its on-chip NPU (Neural Network Processor) offers up to 3.0TOPs computing power.
The TB-RK3399Pro development board has rich external interfaces, including 4 lanes PCIE and Mini PCIE, dual high-speed USB3.0 port Type-C + USB3.0 Type-A, dual MIPI CSI and dual ISP with pixel processing capability up to 1300W pixels, and HDMI2.1, DP1.2, MIPI-DSI and EDP; it also supports 8-channel digital microphone array input.
On the software side, TB-RK3399Pro is pre-installed Android and Linux system, support dual system boot and one-button OS switching. integrated rich AI application development components, providing friendly and concise application programming interface, seamless docking NPU to achieve AI computing hardware acceleration, support Various model inferences such as TensorFlow/TensorFlow lite/Caffe.
Specification
SoC Rockchip RK3399Pro (NPU built-in)
NPU Support 8-bit/16-bit Inference
Deep Learning Support TensorFlow/Caffe Model
CPU Dual Cortex-A72 +Quad Cortex-A53,64-bit CPU
Frequency up to 1.8GHz
GPU Mali-T860MP4 GPU
Memory 6GB LPDDR3
EMMC 32GB eMMC
Support SIM Card, TF Card
USB 2 x USB 2.0 Host, 1 x USB 3.0 Host, 1 x USB 3.0 Type-C
Dual OS Android 8.0 & Fedora 28
RK3399Pro
Dual-core Cortex-A72 up to 1.8GHz; Quad-core Cortex-A53 up to 1.4GHz
NPU up to 3.0TOPS
Mali-T860MP4 GPU
Dual-channel DDR3/DDR3L/LPDDR3/LPDDR4
4K UHD H265/H264/VP9
HDR10/HLG
H264 encoder
Dual MIPI CSI and ISP
USB Type-C and USB 2.0
CPU Big.Little architecture: Dual Cortex-A72 + Quad Cortex-A53, 64-bit CPU
Frequency is up to 1.8GHz
NPU Support 8-bit/16-bit Inference
Support TensorFlow/Caffe Model
GPU Mali-T860MP4 GPU, OpenGL ES1.1/2.0/3.0/3.1, OpenVG1.1, OpenCL, DX11
Supports AFBC (ARM Frame Buffer Compression)
Memory 3GB/6GB LPDDR3
Support eMMC 5.1 with HS400, SDIO 3.0 with HS200
Multi-Media 4K VP9 and 4K 10bits H265/H264 video decoders, up to 60fps
1080P other video decoders (VC-1, MPEG-1/2/4, VP8)
1080P video encoders for H.264 and VP8
Video post processor: de-interlace, de-noise, enhancement for edge/detail/color
Display Dual VOP: one supports 4096x2160 with AFBC supported; the other supports 2560x1600
Dual channel MIPI-DSI (4 lanes per channel)
eDP 1.3 (4 lanes with 10.8Gbps) to support display, with PSR
HDMI 2.0 for 4K 60Hz with HDCP 1.4/2.2
DisplayPort 1.2 (4 lanes, up to 4K 60Hz)
Supports Rec.2020 and conversion to Rec.709
Interface Dual 13M ISP and dual channel MIPI CSI-2 receive interface
USB 3.0 with type-C supported
PCIe 2.1 (4 full-duplex lanes)
Embedded low power MCU for other application
8 channels I2S supports 8 channels RX or 8 channels TX
Shipping list:
1 x TB-RK3399Pro development board with Heatsink (6G+32G eMMC)
1 x Acrylic case with screws
1 x 12V-2A power supply
1 x Type C cable

RETURNS POLICY

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Morbi ut blandit risus. Donec mollis nec tellus et rutrum. Orci varius natoque penatibus et magnis dis parturient montes, nascetur ridiculus mus. Ut consequat quam a purus faucibus scelerisque. Mauris ac dui ante. Pellentesque congue porttitor tempus. Donec sodales dapibus urna sed dictum. Duis congue posuere libero, a aliquam est porta quis.

Donec ullamcorper magna enim, vitae fermentum turpis elementum quis. Interdum et malesuada fames ac ante ipsum primis in faucibus.

Curabitur vel sem mi. Proin in lobortis ipsum. Aliquam rutrum tempor ex ac rutrum. Maecenas nunc nulla, placerat at eleifend in, viverra etos sem. Nam sagittis lacus metus, dignissim blandit magna euismod eget. Suspendisse a nisl lacus. Phasellus eget augue tincidunt, sollicitudin lectus sed, convallis desto. Pellentesque vitae dui lacinia, venenatis erat sit amet, fringilla felis. Nullam maximus nisi nec mi facilisis.

SHIPPING

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Morbi ut blandit risus. Donec mollis nec tellus et rutrum. Orci varius natoque penatibus et magnis dis parturient montes, nascetur ridiculus mus. Ut consequat quam a purus faucibus scelerisque. Mauris ac dui ante. Pellentesque congue porttitor tempus. Donec sodales dapibus urna sed dictum. Duis congue posuere libero, a aliquam est porta quis.

Donec ullamcorper magna enim, vitae fermentum turpis elementum quis. Interdum et malesuada fames ac ante ipsum primis in faucibus.

Curabitur vel sem mi. Proin in lobortis ipsum. Aliquam rutrum tempor ex ac rutrum. Maecenas nunc nulla, placerat at eleifend in, viverra etos sem. Nam sagittis lacus metus, dignissim blandit magna euismod eget. Suspendisse a nisl lacus. Phasellus eget augue tincidunt, sollicitudin lectus sed, convallis desto. Pellentesque vitae dui lacinia, venenatis erat sit amet, fringilla felis. Nullam maximus nisi nec mi facilisis.