NVIDIA Jetson
Ranked 3 of 14 single-board computers by recommenders
Recommended for running AI models and robotics on a small, low-power board with strong GPU performance, though critics say software support is short and poorly maintained.
Recommended for running AI models and robotics on a small, low-power board with strong GPU performance, though critics say software support is short and poorly maintained.
49 people gave an opinion
- recommend it
- 28
- criticize it
- 21
- approval share
- 57%
Recommended in 12 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 28 people recommend itNeeds 10 or more, met.
- 1.3 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 12 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong AI performance for the price
“At this moment in the embedded world Jetson Orin Nano is the best value for money purchase. Absolute beast at the price point.”
Comment from 28 May 2026 in “News about Raspberry Pi 6 and Microcontroller Development – Jeff Geerling” “The entire voice-to-text-to-speech loop runs locally on a sub-$250 Nvidia Jetson Orin Nano.”
Comment from 16 Dec 2025 in “Full AI Voice Agent (Whisper and 700M LLM and NeuTTS) running offline [video]” Good AI compute at low power
“having 40 TOPS of AI compute on an ARM SoC at ~15W opens up capabilities that people don't expect from small hardware”
Comment from 10 Feb 2026 in “Show HN: Local task classifier and dispatcher on RTX 3080(No Ollama, raw Python)” “The computational power of the Jetson Orin Nano enables advanced physical AI models to operate in real time.”
Comment from 27 Feb 2026 on Hacker News Runs local AI models well
“The Orin Nano's 8GB unified memory makes a real difference for running quantized models alongside the agent.”
Comment from 12 Feb 2026 in “Installing OpenClaw on a Jetson Nano” “Fine-tuned Qwen models run surprisingly well on NVIDIA Jetson hardware”
Comment from 4 Mar 2026 in “Qwen3.5 Fine-Tuning Guide – Unsloth Documentation” Works out of the box
“it came pre-configured with everything (Telegram, browser automation, cron jobs) working out of the box”
Comment from 10 Feb 2026 in “Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?” “Runs Linux out of the box.”
Comment from 11 May 2026 in “Running local models on an M4 with 24GB memory”
What people warn about
Each mark is one comment
Software stops getting updates
“they show up, then within 2-3 years they're abandonware, trapped on an ancient kernel and EOL Ubuntu distro”
Comment from 15 Apr 2026 in “The Orange Pi 6 Plus” “Nvidia can barely scrape together one Ubuntu release per Jetson generation, it's beyond embarrassing”
Comment from 6 Jun 2026 in “Nvidia is proposing a beast of a CPU system for Windows PCs” “great hardware, unusable because the stack worked once when shipped then wasn't maintained.”
Comment from 15 Apr 2026 in “The Orange Pi 6 Plus” - Comment from 1 Feb 2026 in “Nvidia's 10-year effort to make the Shield TV the most updated Android device”
- Comment from 7 Jun 2026 in “Nvidia is proposing a beast of a CPU system for Windows PCs”
Unclear support and poor documentation
“Jetson is such a confusing product and it's difficult to tell exactly what they're supporting.”
Comment from 7 Jan 2026 in “Microsoft probably killed my Snapdragon Dev Kit” “their whole approach is just stupid, and they don't provide any documentation”
Comment from 7 Jul 2026 in “AMD Ryzen AI Halo – $4k AI Dev Kit” ARM-specific bugs and thermal issues
“ARM-specific bugs and thermal constraints that don't show up in testing”
Comment from 4 Mar 2026 in “Agentic Engineering Patterns” “absolutely awful on the Jetson Nano and Orin boards I worked on”
Comment from 28 May 2026 in “News about Raspberry Pi 6 and Microcontroller Development – Jeff Geerling”
Other single-board computers people recommend
The four most recommended other single-board computers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Raspberry Pi | 425 | 277 | 61% | 12 | 5.5 yrs35 owners | — |
| Raspberry Pi Zero | 77 | 23 | 77% | 12 | 8 yrs6 owners | Approved |
| NVIDIA JetsonThis page | 28 | 21 | 57% | 12 | — | — |
| Orange Pi 6 Plus | 18 | 30 | 38% | 5 | — | — |
| Raspberry Pi 2 | 12 | 2 | 86% | 8 | 9 yrs5 owners | Approved |
What people said
40 of the 59 comments that mention it, newest first. Each links to the original comment.
“Nvidia has the momentum with Tegra and Jetson”
“5 token/sec is a little painful though.”
“A Jetson Orin Nano would seem to be a better choice for a robot.”
“One very efficient option today is to have the cheapest Jetson (Orin Nano) run the classical robotics stack”
“you get full-fat CUDA support without sacrificing Vulkan drivers”
“the ARM SoC portion of a jetson board couldn't even keep up with broadcom/rockchip SoCs”
“I have also used NVIDIA Jetson SBCs, with NVIDIA Volta GPUs.”
“their whole approach is just stupid, and they don't provide any documentation”
“I've been dealing with their Jetson line for a couple of years now, and it still sucks.”
“comparable single core speed but with two more cores, LPDDR5 with 5x as much memory bandwidth”
“so yea it works on arm like a charm”
“Nvidia can barely scrape together one Ubuntu release per Jetson generation”
“Nvidia can barely scrape together one Ubuntu release per Jetson generation, it's beyond embarrassing”
“At this moment in the embedded world Jetson Orin Nano is the best value for money purchase. Absolute beast at the price point.”
“Nowadays upstream Linux with UEFI mostly works, with their out of tree drivers.”
“absolutely awful on the Jetson Nano and Orin boards I worked on”
“the Jetson has a faster CPU (newer a78ae cores rather than a76)”
“Runs Linux out of the box.”
“similar to what Nvidia did with the Jetson and Tegra SOCs”
“great hardware, unusable because the stack worked once when shipped then wasn't maintained.”
“they show up, then within 2-3 years they're abandonware, trapped on an ancient kernel and EOL Ubuntu distro”
“I would choose Jetson for anything computationally intensive”
“faster at prefill and decode, as well as cheaper for home installation”
“ARM-specific bugs and thermal constraints that don't show up in testing”
“Fine-tuned Qwen models run surprisingly well on NVIDIA Jetson hardware”
“The computational power of the Jetson Orin Nano enables advanced physical AI models to operate in real time.”
“something from the Jetson series would make more sense.”
“That can be combined with nvidia orin like sbc as a good starting point.”
“The Orin Nano's 8GB unified memory makes a real difference for running quantized models alongside the agent.”
“it came pre-configured with everything (Telegram, browser automation, cron jobs) working out of the box”
“having 40 TOPS of AI compute on an ARM SoC at ~15W opens up capabilities that people don't expect from small hardware”
“Even the latest and greatest cameras will lag the processing power of something like a Jetson Nano”
“many other devices by Nvidia like the Jetson boards never get any long term updates”
“Jetsons are great for very small-scale self-contained tasks”
“I think the Jetson Orin Nano is a better purchase for this application.”
“Jetson is such a confusing product and it's difficult to tell exactly what they're supporting.”
“Ubuntu is supporting my NVidia Jetson going forward after NVidias official support period ends”
“I have no reason to think this would be different with the Orin and Thor series”
“The entire voice-to-text-to-speech loop runs locally on a sub-$250 Nvidia Jetson Orin Nano.”
“pretty fast and ARM based”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.