Nvidia Jetson Nano vs Raspberry Pi 4
Comparison and Benchmark
Introduction
NVIDIA announced the Jetson Nano Developer Kit at the 2019 NVIDIA GPU Technology Conference (GTC), a $99 [USD] computer available now for embedded designers, researchers, and DIY makers, delivering the power of modern AI in a compact, easy-to-use platform with full software programmability. NVIDIA® Jetson Nano™ Developer Kit is a small, powerful computer that lets you run multiple neural networks in parallel for applications like image classification, object detection, segmentation, and speech processing.
Raspberry Pi 4 Model B is the latest product in the popular Raspberry Pi range of computers. Raspberry Pi 4 was released on June 2019. It offers ground-breaking increases in processor speed, multimedia performance, memory, and connectivity compared to the prior-generation Raspberry Pi 3 Model B+, while retaining backwards compatibility and similar power consumption. For the end user, Raspberry Pi 4 Model B provides desktop performance comparable to entry-level x86 PC systems.
In this comparison, we will be comparing the highest spec model of Jetson Nano with the highest spec model of Raspberry Pi 4B.
Platform | CPU | GPU | Memory | Storage | MRP |
---|---|---|---|---|---|
Jetson Nano | 4x ARM Cortex A57 @ 1.43 GHz | 128x Maxwell @ 921 MHz (472 GFLOPS) | 4GB LPDDR4 – 1600 | Micro SD | $99.00 |
Raspberry Pi 4 Model B | 4x ARM Cortex A72 @ 1.5GHz | Broadcom VideoCore VI | 2GB / 4GB / 8GB LPDDR4 – 3200 | Micro SD | $55.00 (4GB RAM) $75.00 (8GB RAM) |
Jetson Nano vs Raspberry Pi 4 Model B Specifications
Features | Jetson Nano 4GB | Jetson Nano 2GB | Raspberry Pi 4 B |
---|---|---|---|
CPU | ARM Cortex-A57 (quad-core) @ 1.43GHz | ARM Cortex-A57 (quad-core) @ 1.43GHz | Broadcom BCM2711, quad-core Cortex-A72 (ARM v8) 64-bit SoC @ 1.5GHz |
GPU | 128-core NVIDIA Maxwell @ 921MHz | 128-core NVIDIA Maxwell @ 921MHz | Broadcom VideoCore VI |
DL | NVIDIA GPU support (CUDA, cuDNN, TensorRT) | NVIDIA GPU support (CUDA, cuDNN, TensorRT) | |
Memory | 4GB 64-bit LPDDR4 @ 1600MHz | 25.6 GB/s | 2GB 64-bit LPDDR4 @ 1600MHz | 25.6 GB/s | 2GB, 4GB or 8GB LPDDR4-3200 SDRAM with on-die ECC |
Storage | MicroSD card | MicroSD card | MicroSD card |
Vision | NVIDIA GPU support (CUDA, VisionWorks, OpenCV) | NVIDIA GPU support (CUDA, VisionWorks, OpenCV) | OpenGL ES 3.0 Graphics |
Encoder | 4Kp30 | 4x 1080p30 | 9x 720p30 (H.264/H.265) | 4Kp30 | 4x 1080p30 | 9x 720p30 (H.264/H.265) | H.264 (1080p30) |
Decoder | 4Kp60 | 2x 4Kp30 | 8x 1080p30 | 18x 720p30 (H.264/H.265) | 4Kp60 | 2x 4Kp30 | 8x 1080p30 | 18x 720p30 (H.264/H.265) | H.265 (4Kp60) | H.264 (1080p60) |
Camera | 2x MIPI CSI-2 connectors | 1x MIPI CSI-2 connector | 1× MIPI CSI Connector |
Display | HDMI and DP | HDMI | 2× micro-HDMI (4kp60) | 1× MIPI DSI |
Wireless | M.2 Key-E Empty Slot | 802.11ac wireless | 2.4 GHz and 5.0 GHz 802.11ac | Bluetooth 5.0 |BLE |
Ethernet | 10/100/1000 BASE-T Ethernet | Gigabit Ethernet | Gigabit Ethernet |
USB | 4x USB 3.0 A | 1x USB 2.0 Micro-B | 1x USB 3.0 A | 2x USB 2.0 A | USB 2.0 Micro-B | 2x USB 3.0 A | 2x USB 2.0 A |
CAN | NA | NA | NA |
Misc IO | UART, SPI, I2C, I2S, GPIOs | UART, SPI, I2C, I2S, GPIOs | UART, SPI, I2C, GPIO |
Thermals | -25°C to 80°C | -25°C to 80°C | 0°C – 50°C |
Power | 5V / 5-10W | 5V / 5-10W | 5V / 10-15W |
Features | Jetson Nano 4GB | Jetson Nano 2GB | Raspberry Pi 4 B |
Jetson Nano Product Offer
Jetson Nano 2GB can be purchased from official channels at a price of 55$ or ₹4,900 and Jetson Nano 4GB at a price of 99$ or ₹9,300.
In the box of Jetson Nano
- 80x100mm Reference Carrier Board, complete devkit with Module and Heatsink weighs 138 grams
- Jetson Nano Module with a passive heatsink [ Upgradable to Active Cooling ]
- Card Board Pop-Up Stand
- Getting Started Paper Guide
- No SD-Card, No Power Input Selection Jumper
What You Will Need Extra for Jetson Nano
- Power Supply
- 5V⎓2A Micro-USB adapter ( Adafruit GEO151UB ) [ I Used One-Plus 6 Charger ]
- 5V⎓4A DC Barrel Jack Adapter, 5.5mm OD x 2.1mm ID x 9.5mm Length, Center-Positive ( Adafruit 1446 ) [ I Used a Belkin 5V⎓4A ]
- MicroSD card ( 16GB UHS-1 Minumum ) [ OS will Occupy ~12.5GB ]
- A Full HD 1080p or Above Monitor with HDMI or DP Input
- A Computer to Flash the SD Card
Raspberry Pi 4 B Product Offer
Raspberry Pi 4 B can be purchased from official channels at a price of $35 or ₹3,200 for 2GB model, $55 or ₹4,800 for 4GB model and $75 or ₹6,800 for 8GB model.
In the box of Raspberry Pi 4 B
- 85x56mm Board weighs 52 grams
- Getting Started Paper Guide
- No SD-Card, No Power Supply
Picture Credit : Adafruit
What you will need extra for Raspberry Pi 4 B
- Power Supply
- 5V⎓3A USB C adapter
- MicroSD card ( 16GB UHS-1 Minumum )
- A Full HD 1080p or Above Monitor with HDMI Input
- A Computer to Flash the SD Card
- Micro HDMI to HDMI Cable
Price Comparison Jetson Nano vs Raspberry Pi 4
Port Comparison
Jetson Nano 4GB | Jetson Nano 2GB | Raspberry Pi 4 B |
---|---|---|
MicroSD Card Slot | MicroSD Card Slot | MicroSD Card Slot |
40-pin GPIO Expansion Header | 40-pin GPIO Expansion Header | 40-pin GPIO Expansion Header |
Micro USB B | Micro USB B | USB C |
Gigabit Ethernet Port | Gigabit Ethernet Port | Gigabit Ethernet Port |
4x USB 3.0 A | 1x USB 3.0 A | 2x USB 2.0 A | 2x USB 3.0 A | 2x USB 2.0 A |
HDMI | Display Port | HDMI | 2x Micro HDMI |
DC Barrel Jack Power Input | NA | NA |
2x MIPI CSI | 1x MIPI CSI | 1x MIPI CSI |
NA | NA | 1x MIPI DSI |
GPIO Header Comparison Jetson Nano vs Raspberry Pi 4
Nvidia has Intelligently kept the Jetson Nano GPIO the same as Raspberry Pi 4 B as this will help them to capture the market easily by supporting most of the Raspberry Pi Hats and Accessories Out of the Box. They also have placed the GPIO Header J41 is such a way that all the Hats protrude outwards as there is no Space to accommodate Hats on the PCB Side, unlike Raspberry Pi.
Name | Pin | Pin | Name |
---|---|---|---|
3.3 VDC Power | 1 | 2 | 5.0 VDC Power |
I2C_2_SDA | 3 | 4 | 5.0 VDC Power |
I2C_2_SCL | 5 | 6 | GND |
AUDIO_MCLK | 7 | 8 | UART_2_TX |
GND | 9 | 10 | UART_2_RX |
UART_2_RTS | 11 | 12 | I2S_4_SCLK |
SPI_2_SCK | 13 | 14 | GND |
LCD_TE | 15 | 16 | SPI_2_CS1 |
3.3 VDC Power | 17 | 18 | SPI_2_CS0 |
SPI_1_MOSI | 19 | 20 | GND |
SPI_1_MISO | 21 | 22 | SPI_2_MISO |
SPI_1_SCK | 23 | 24 | SPI_1_CS0 |
GND | 25 | 26 | SPI_1_CS1 |
I2C_1_SDA | 27 | 28 | I2C_1_SCL |
CAM_AF_EN | 29 | 30 | GND |
GPIO_PZ0 | 31 | 32 | LCD_BL_PWM |
GPIO_PE6 | 33 | 34 | GND |
I2S_4_LRCK | 35 | 36 | UART_2_CTS |
SPI_2_MOSI | 37 | 38 | I2S_4_SDIN |
GND | 39 | 40 | I2S_4_SDOUT |
Name | Pin | Pin | Name |
Jetson Nano 4GB Vs Raspberry Pi 4 B 8GB Benchmark
Phoronix Test Suite :
So I Started with Some of the Standard Test of Phoronix Test Suite. You can also run the same test by executing the below commands.
sudo apt-get install -y php-cli php-xml
# Download PTS https://www.phoronix-test-suite.com/ and Install
phoronix-test-suite benchmark 1809111-RA-ARMLINUX005
# Accept for Dependency Installation and Wait a few hours, Test Result is available at :
~/.phoronix-test-suite/test-results/
Test | Raspberry Pi 4 B 8GB | Jetson Nano 4GB | Notes |
---|---|---|---|
Tinymembenc Standard Memcpy | 2526.8 MB/s | 3501 MB/s | MB/s > Higher Is Better |
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping | 32.3075 FPS | 41.00 FPS | FPS > Higher Is Better |
7-Zip Compression Compress Speed Test | 3701 MIPS | 3501 MIPS | MIPS > Higher Is Better |
C-Ray Total Time – 4K, 16 Rays Per Pixel | 609.431 Seconds | 932 Seconds | Seconds < Lower Is Better |
Primesieve 1e12 Prime Number Generation | 519.238 Seconds | 468 Seconds | Seconds < Lower Is Better |
AOBench Size: 2048 x 2048 | 125.643 Seconds | 187 Seconds | Seconds < Lower Is Better |
FLAC Audio Encoding WAV To FLAC | 85.805 Seconds | 104.01 Seconds | Seconds < Lower Is Better |
LAME MP3 Encoding WAV To MP3 | 124.952 Seconds | 144.21 Seconds | Seconds < Lower Is Better |
Perl Pod2html | 0.58082059 Seconds | 0.7114 Seconds | Seconds < Lower Is Better |
Redis GET | 491168.39 Requests Per Second | 568431 Requests Per Second | Requests Per Second > Higher Is Better |
PyBench Total For Average Test Times | 5673 Milliseconds | 7080 Milliseconds | Milliseconds < Lower Is Better |
Test | Raspberry Pi 4 B 8GB | Jetson Nano 4GB | Notes |
Compared to Raspberry Pi 4B Jetson Nano is expensive in the same RAM configuration. For day to day computing activities and embedded work and projects, Raspberry Pi is a better value for money. Only when projects demand GPU usage or ML or AI applications that can benefit from CUDA cores you should consider Jetson Nano.
Raspberry Pi 4 B is a better Linux PC with better value at 8GB and 4GB RAM. Also, the plenty of USB 3.0 Ports, Integrated WiFi, Bluetooth and Dual Monitor Configuration is really that most user wants in their day to day use PC.
Raspberry Pi 4 B is a better value for money device.
Jetson Nano is more suited for this because of the availability of CUDA cores, GPU and multiple video encoder and decoder.
4 Comments
AA KK · September 18, 2021 at 1:43 am
The whole point of Jetson is the cuda cores and these are not benchmarked here. Dissapointing!
Crazy Engineer · September 20, 2021 at 9:52 am
Explore the other article on Jetson Nano Unboxing, It is discussed there.
ola · December 4, 2022 at 2:01 am
hello
I need the author name
because I need it as reference to my university project
(very important)
Crazy Engineer · December 4, 2022 at 7:39 pm
Author Name : Arnab Kumar Das