BIOSTAR announced the AI-NONXS Developer Kit on July 14, 2025, as an edge-AI platform for system integrators and developers. Its specifications list carrier-board configurations for Jetson Orin NX and Orin Nano modules, including configurations enabled for NVIDIA’s JetPack 6.2 Super Mode. The kit’s stated features include camera, network, serial, CAN, and M.2 expansion connections; the announcement does not establish that a Jetson module, power supply, or other accessories are included in a retail package.
What the BIOSTAR AI-NONXS Developer Kit is
The AI-NONXS is an edge-computing platform built around NVIDIA Jetson Orin NX or Orin Nano system-on-modules (SoMs). BIOSTAR positions it for system integrators and AI software developers deploying applications in settings such as smart manufacturing, retail, automated warehouses, smart cities, transportation, and agriculture. It is not the separate NVIDIA Jetson Orin Nano Super Developer Kit.
BIOSTAR lists Linux and NVIDIA JetPack 6.2 support, with Orin NX and Orin Nano modules enabled for Super Mode. BIOSTAR cites workloads including LLMs, SLMs, vision-language models, vision transformers, Stable Diffusion, and DeepSeek R1. Those are vendor-stated target workloads, not a guarantee that every model will run at a particular speed or within a particular power or thermal limit.
Which Jetson modules and performance figures BIOSTAR lists
BIOSTAR’s specifications list four module configurations and associate each with an AI-performance figure. These are BIOSTAR’s figures; they should not be treated as direct equivalents to NVIDIA’s Super Mode results or as independently measured performance of a complete AI-NONXS system.
#1 Best Overall
- 【Core Parameters】★AI Perf: 34/67 TOPS ★GPU:1024-core official Ampere architecture GPU with 32 Tensor Cores ★CPU:6-core Arm Corte-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 ★Memory:8GB 128-bit LPDDR5 68 GB/s ★Storage: external NVMe via M.2 Key M
- 【Empowered by Large Al Model, Enhanced Human-Computer Interaction】Jetson Orin Super leverages three AI models and incorporates an AI voice interaction module. This multimodal visual system matches the scene being described, enabling environmental awareness and AI visual gameplay. Combined with a large-scale voice module and camera, it enables speech-to-text, semantic analysis, natural conversation, and real-time video analysis, enabling advanced embodied AI applications.
- 【AI Upgrade】Jetson Orin Nano series modules are compact in size but can deliver up to 34-67 TOPS of AI performance, with power consumption ranging from 7 watts to 25 watts. Compared to the Jetson Nano B01, it offers up to 80 times the performance and sets a new standard for entry-level edge AI.
- 【Highly compatible carrier board】Yahboom's carrier board is fully compatible with orin nano module. Compared to carrier boards that use Jetson Nano on the market, the newly upgraded circuit supports 25W power mode, which enables larger and more complex neural networks and fully leverages the performance of the core module. The resources, size, and interfaces of the Yahboom carrier board are consistent with the official board, with the only difference addition of power switch button.
- 【Tutorial materials provided】The JETSON system based on Ubuntu 22.04 provides a complete desktop Linux environment with accelerated graphics, supporting CUDA 12.6, TensorRT 10.7.0, cuDNN 9.6.0, OpenCV 4.10.0, etc. The performance on AI LLM, VLM and visual Transformer is significantly improved compared with the previous generation.
| Module configuration | BIOSTAR-listed AI performance | Memory bandwidth listed by BIOSTAR | HDMI |
|---|---|---|---|
| Jetson Orin NX 16GB | 100 TOPS | 102.4 GB/s | 2.1 |
| Jetson Orin NX 8GB | 70 TOPS | 102.4 GB/s | 2.1 |
| Jetson Orin Nano 8GB | 40 TOPS | 68 GB/s | 1.4 |
| Jetson Orin Nano 4GB | 20 TOPS | 34 GB/s | 1.4 |
These are configurations in BIOSTAR’s specification, not confirmation that every kit sold includes the corresponding module. NVIDIA’s current Jetson module page gives family-level maxima of up to 157 TOPS for Orin NX and up to 67 TOPS for Orin Nano; those maxima do not mean every AI-NONXS configuration reaches them. TOPS figures can also depend on how performance is counted and on the module’s operating mode, so compare complete configurations and workloads rather than treating unlike figures as interchangeable.
What NVIDIA Super Mode changes
NVIDIA’s January 16, 2025 technical post says JetPack 6.2 adds Super Mode for production Orin Nano and Orin NX modules and can deliver up to 2× higher generative-AI model performance. This is an NVIDIA vendor claim, not a guaranteed application-level improvement. NVIDIA’s results vary with the model and configuration.
The software introduces higher-power reference modes, including 25W and MAXN SUPER options for Orin Nano and 40W and MAXN SUPER options for Orin NX, depending on the module. MAXN SUPER is uncapped: if module power exceeds its thermal design budget, the module may throttle. NVIDIA recommends tuning a custom power mode for the use case to balance performance, power draw, and thermal stability.
In practice, assess a build using the exact module and memory capacity, its power mode and cooling, the target model, and the required camera, network, and storage connections. A mode that raises peak performance may also demand more power and thermal headroom. The AI-NONXS announcement does not establish application-specific benchmarks for these combinations.
Rank #2
- 【Core Parameters】★AI Perf:34-67 TOPS ★GPU:512-core NVIDIA Ampere architecture GPU with 16 Tensor Cores ★CPU:6-core Arm Corte-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3 ★Memory:4GB 64-bit LPDDR5 51 GB/s ★Storage: external NVMe via M.2 Key M (NOTE:SUB Board No SD Card Slot)
- 【Empowered by Large Al Model, Enhanced Human-Computer Interaction】Jetson Orin Super leverages three AI models and incorporates an AI voice interaction module. This multimodal visual system matches the scene being described, enabling environmental awareness and AI visual gameplay. Combined with a large-scale voice module and camera, it enables speech-to-text, semantic analysis, natural conversation, and real-time video analysis, enabling advanced embodied AI applications.
- 【AI Upgrade】Jetson Orin Nano series modules are compact in size but can deliver up to 34-67 TOPS of AI performance, with power consumption ranging from 7 watts to 25 watts. Compared to the Jetson Nano B01, it offers up to 80 times the performance and sets a new standard for entry-level edge AI.
- 【Highly compatible carrier board】Yahboom's carrier board is fully compatible with orin nano module. Compared to carrier boards that use Jetson Nano on the market, the newly upgraded circuit supports 25W power mode, which enables larger and more complex neural networks and fully leverages the performance of the core module. The resources, size, and interfaces of the Yahboom carrier board are consistent with the official board, with the only difference addition of power switch button.
- 【Tutorial materials provided】The JETSON system based on Ubuntu 22.04 provides a complete desktop Linux environment with accelerated graphics, supporting NVIDI-ACUDA 12.6, TensorRT 10.7.0, cuDNN 9.6.0, OpenCV 4.10.0, etc. The performance on AI LLM, VLM and visual Transformer is significantly improved compared with the previous generation.
Connections and expansion
BIOSTAR’s listed interfaces make the board relevant where an edge system needs more than a basic development-board setup. Confirm the exact carrier and module configuration before designing around any feature.
- Cameras: Dual 4-lane MIPI CSI connections for compatible camera hardware.
- Networking: One Gigabit Ethernet port and one 2.5GbE port; PoE is optional.
- USB and display: Four USB Type-A ports and HDMI, with the version depending on the module family: HDMI 2.1 for NX and HDMI 1.4 for Nano.
- Storage: An M.2 Key-M slot for NVMe SSDs in 2242, 2260, or 2280 sizes.
- Wireless and cellular: M.2 Key-E for 2230 Wi-Fi/Bluetooth modules and Key-B for 3042/3052 4G LTE/5G modules, plus a Nano SIM slot.
- Industrial and system I/O: Serial and CAN interfaces, TPM 2.0, a 3.5 mm headset jack, digital microphone and speaker headers, and power, recovery, and reset buttons.
Power, dimensions, and operating temperature
BIOSTAR lists a 12–20 V DC input and board dimensions of 130 × 100 mm. Its July 14, 2025 announcement gives an operating-temperature range of –20°C to 60°C, but does not make clear which exact module, enclosure, or cooling configuration the range applies to. Treat it as an attributed platform claim and confirm thermal limits for the intended build.
What to verify before choosing the kit
The available BIOSTAR material describes the platform and its interfaces, but does not establish price, retail availability, or package contents. Before procurement, ask BIOSTAR or its authorized distributor to confirm the exact bundle and configuration.
Quick Recap
- Whether the quoted item includes the carrier board only or also a Jetson module, power supply, storage, antennas, or other accessories.
- Which module and memory capacity are fitted, and which performance figure and HDMI version apply.
- Whether the desired Super Mode and JetPack software configuration are supported for that module.
- Power-supply requirements, cooling provisions, and operating-temperature limits for the complete assembly.
- Compatibility of the selected MIPI cameras, M.2 devices, cellular modem, and other peripherals.
Sources
- BIOSTAR announcement, July 14, 2025
- BIOSTAR AI-NONXS specifications
- NVIDIA technical post on JetPack 6.2 Super Mode, January 16, 2025
- NVIDIA Jetson Orin Nano power and performance documentation
- NVIDIA Jetson Orin module lineup
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Recommended Free Tools
