HomeUse cases › On-Device AI Computing
AI / Edge

On-Device AI Computing

Local inference for robotics, smart home and content creation, where latency, privacy or connectivity rules out sending data to a server.

Cloud inference adds latency, a per-request cost, and a dependency on a network that may not be there. For robotics control loops and for anything handling video of people, the round trip is often the problem rather than the model.

How RISC-V addresses it

Local firstThe K3 is specified at 60 TOPS INT4 from eight dedicated A100 AI cores, with LPDDR5 up to 32 GB at 51 GB/s. That is enough memory to hold quantized models that would otherwise be split across a network.
Mainline softwareRVA23 compliance means the K3 runs Ubuntu 26.04 LTS natively, without out-of-tree patches. Your ML stack is a standard package install, not a vendor fork you have to maintain.
Vision and IOFour MIPI-CSI inputs supporting up to 12 cameras, 4K@180fps decode and 4K@90fps encode. Four TSN-capable Gigabit MACs and eight lanes of PCIe Gen3 for accelerator or NVMe expansion.

Recommended parts

SpacemiT K3
60 TOPS RISC-V AI SoC, RVA23 compliant, mainline Linux
CPU 8x X100 @ 2.4 GHz, 4-issue out-of-order; AI cores 8x A100, 60 TOPS INT4, 1024-bit RVV 1.0; Compliance RVA23, RV Hypervisor 1.0, AIA, IOMMU
View product →

Fit assessment

Good fit for: Robotics, smart home hubs, private assistants, on-premise content generation, machine vision at the edge.
Check before committing: The K3 is specified at 15-25 W TDP. Plan the thermal design before you plan the enclosure — this is not a passively cooled part.

Questions

Can it really run a 30B model?

A quantized 30B model, yes — that is what 60 TOPS INT4 and 32 GB of LPDDR5 are for. Token throughput depends on the quantization and the runtime; benchmark your own model before committing to a figure.

Is it a drop-in for Jetson Orin Nano?

The K3 is pin-compatible with Jetson Orin Nano, which makes carrier board migration realistic. Software migration is a separate piece of work.

Tell us the deployment and the volume. We will confirm part availability, lead time and pricing.
Request a quote