NVIDIA Gives Jetson Nano Dev Kit a Trim: 2GB Model For $59
by Ryan Smith on October 5, 2020 9:00 AM EST- Posted in
- NVIDIA
- Jetson
- Jetson Nano
- GTC 2020.5
- Tegra TX1
As part of this morning’s fall GTC 2020 announcements, NVIDIA is revealing that they are releasing an even cheaper version of their budget embedded computing board, the Jetson Nano. Initially introduced back in 2015 as the Jetson TX1, an updated version of NVIDIA’s original Jetson kit with their then-new Tegra X1 SoC, the company has since kept the Jetson TX1 around in various forms as a budget option. Most recently, the company re-launched it in 2019 as the Jetson Nano, their pint-sized, $99 entry level developer kit.
Now, NVIDIA is lowering the price tag on the Jetson Nano once again with the introduction of a new, cheaper SKU. Dubbed the Jetson Nano 2GB, this is a version of the original Jetson Nano with 2GB of DRAM instead of 4GB. Otherwise the performance of the kit remains unchanged from the original Nano, with 4 Cortex-A57 CPU cores and the 128 CUDA core Maxwell GPU providing the heavy lifting for CPU and GPU compute, respectively.
NVIDIA Jetson Family Specifications | ||||||
Xavier NX (15W) |
AGX Xavier | Jetson Nano (4GB) | Jetson Nano (2GB) | |||
CPU | 4x/6x Carmel @ 1.4GHz or 2x Carmel @ 1.9GHz |
8x Carmel @ 2.26GHz |
4x Cortex-A57 @ 1.43GHz |
4x Cortex-A57 @ 1.43GHz |
||
GPU | Volta, 384 Cores @ 1100MHz |
Volta, 512 Cores @ 1377MHz |
Maxwell, 128 Cores @ 920MHz |
Maxwell, 128 Cores @ 920MHz |
||
Accelerators | 2x NVDLA | 2x NVDLA | N/A | N/A | ||
Memory | 8GB LPDDR4X, 128-bit bus (51.2 GB/sec) |
16GB LPDDR4X, 256-bit bus (137 GB/sec) |
4GB LPDDR4, 64-bit bus (25.6 GB/sec) |
2GB LPDDR4, 64-bit bus (25.6 GB/sec) |
||
Storage | 16GB eMMC | 32GB eMMC | 16GB eMMC | microSD | ||
USB | 4x USB-A 3.1 Gen 2 | 2x USB-C 3.1 1x USB-A 3.0 |
4x USB-A 3.0 | 1x USB-A 3.0 2x USB-A 2.0 1x USB-C (Power) |
||
AI Perf. | 21 TOPS | 32 TOPS | N/A | N/A | ||
Dimensions | 45mm x 70mm | 100mm x 87mm | 45mm x 70mm | 45mm x 70mm | ||
TDP | 15W | 30W | 10W | 10W | ||
Price | $399 | $699 | $99 | $59 |
Meanwhile, though not mentioned in NVIDIA’s official press release, it looks like the company has simplified the carrier board a bit as part of their process of getting the price tag down. Relative to the original 4GB Nano, the Nano 2GB is pictured without a DisplayPort output, and with one fewer USB port. Furthermore those USB ports are no longer blue, hinting that they are USB 2.0 instead of USB 3.0 with NVIDIA confirming that just 1 port is USB 3.0-capable, while the other two are USB 2.0. Finally, the barrel power connector has been replaced with a USB Type-C connector, and it looks like various pins have also been removed.
Overall, NVIDIA is pitching the cost-reduced Jetson Nano as a true starter kit for embedded computing, suitable for early training and learning. Despite receiving a minor neutering, the Nano 2GB can still run all of NVIDIA’s Jetson SDKs, allowing it to be used as a stepping stone of sorts towards learning NVIDIA’s NVIDIA’s ecosystem, and eventually moving on to their more powerful products like their GPU accelerators and Jetson Xavier NX kits. Ultimately, with their efforts to position it as a starter kit for teaching purposes, I imagine NVIDIA is gunning for the educational market, particularly with the continued uptick in STEM-focused programs.
The kit will go on sale later this month through NVIDIA’s usual distribution channels.
Source: NVIDIA
10 Comments
View All Comments
André - Monday, October 5, 2020 - link
Still no Wi-Fi or Bluetooth?voicequal - Monday, October 5, 2020 - link
No wireless built on to the board, but spec page lists an included 802.11ac wireless (USB) adapter and extension cable. But it's not included in all regions initially.Samus - Monday, October 5, 2020 - link
This is super cool I just wish they hadn't given it a 6-7 year old GPU architecture. Would it really have hit their bottom line to incorporate a Volta 384 core GPU with a 4xA57?voicequal - Monday, October 5, 2020 - link
Many applications would probably be bandwidth limited with Volta. Hence twice the bandwidth on the Xavier NX.PeachNCream - Tuesday, October 6, 2020 - link
Its like a Raspberrry Pi 4 with less RAM, no wireless networking, poorer industry support, and a higher price. Unless you have a specific need for this sort of SBC, you're better off with some sweet, yummy pie.webdoctors - Tuesday, October 6, 2020 - link
Since its cheaper than a Shield or Nintendo Switch can you hack it to do any of those functions?sing_electric - Wednesday, October 7, 2020 - link
It's the same SoC as a Shield but it looks like its gimped in any number of ways; I think it's got half the performance as the 2015 Shield? And it lacks an enclosure and any kind of onboard storage (or a remote). By the time you add those things back, you're not *that* far from what the Shield would cost (particularly since the Jetson seems like it runs pretty warm, so you can't just assume a PLA 3D printed enclosure would hold up).sing_electric - Wednesday, October 7, 2020 - link
Eh, it depends on what your needs are. If you're OK with binary blobs and want to learn ML tools on a device with some GPIO pins, this looks like it's a pretty decent choice. Certainly its outclassed by any number of SBCs at around the same price point in some respects; but the real selling point here is that its designed to be an entry to Nvidia's tools, which are pretty widely-used.Aboold60 - Monday, October 19, 2020 - link
Hey, thanks for providing good or useful information and also for price details. This will be helpful for many people, I would like to read these kind of good posts. Like yesterday I saw a post about <a href="https://edubirdie.net/">edubridie</a>... there we can see best writing services. So I feel very happy whenever I see these type of useful posts, thanks again.Aboold60 - Tuesday, October 20, 2020 - link
https://ceasefiremagazine.co.uk">great