← All hardware
Qualcomm's accessible on-ramp to edge AI for IoT and robotics.
Pros
- Strong power efficiency and connectivity from Qualcomm silicon
- Multiple kit tiers and a Lite option
- Backed by Qualcomm AI Hub and Edge Impulse tooling
Cons
- Smaller robotics ecosystem than NVIDIA Jetson
- NPU TOPS modest vs high-end accelerators
- Software/tooling less mature for newcomers
✓ Where it shines / best for
- IoT edge devices and connected products
- Camera-based robotics and vision (Vision Kit)
- Developers wanting efficient on-device AI with connectivity
✕ Not the best fit for
- On-device large generative models
- Projects requiring NVIDIA CUDA/Isaac ecosystem
- Maximum raw-TOPS workloads
Features
- ✓ Qualcomm QCS6490 SoC with Hexagon NPU (~12-13 TOPS class)
- ✓ Kryo CPU and Adreno GPU for heterogeneous compute
- ✓ Core Kit and Vision Kit (with camera sensors) options
- ✓ Higher inferences/sec and multi-network support
- ✓ Wi-Fi 6/6E and connectivity for IoT
- ✓ Qualcomm AI Hub and Linux/Android support
- ✓ Integrated with Edge Impulse platform
- ✓ RB3 Gen 2 Lite (QCS5430) lower-cost variant
Pricing
| Plan | Price | Billing | Notes |
|---|---|---|---|
| RB3 Gen 2 Core Kit | $439 | one-time | Base QCS6490 development kit (current Thundercomm store price; launched at $399) |
| RB3 Gen 2 Vision Kit | $639 | one-time | Includes high- and low-resolution camera sensors (current Thundercomm store price; launched at $599) |
Pricing verified from the official source. Prices change often — confirm on the vendor's site before buying.
Specifications
| power | Low-power edge |
| memory | LPDDR (kit-dependent) |
| form_factor | Development kit (Core / Vision) |
| architecture | Qualcomm QCS6490 (Kryo CPU + Adreno GPU + Hexagon NPU) |
| ai_performance | ~12-13 TOPS class NPU |
Sponsored
A full review is being generated for this product and will appear here shortly.