AI TrustMark

Edge inference companies, products & suppliers

Running models at the edge (gateways, stores, plants) as an inference product, not embedded chips or on-device assistants. Jobs: store/plant inference; gateway runtimes; fleet of edge nodes.

What is Edge inference?

Running models at the edge (gateways, stores, plants) as an inference product, not embedded chips or on-device assistants. Jobs: store/plant inference; gateway runtimes; fleet of edge nodes.

What problems does it solve?

Cloud round-trips are too slow, costly or private for the site.

Typical business use cases

  • Store/plant inference
  • Gateway runtimes
  • Fleet of edge nodes

Important capabilities

  • Hardware targets
  • Model packaging
  • Fleet ops

What buyers should evaluate

  • Hardware
  • Update of models
  • What data leaves the site

Risks and governance considerations

Edge boxes that still ship every frame to the cloud.

Procurement checklist

  • Data leaving site
  • Hardware
  • Updates

Relevant AI Trustmark assurance

AI Trustmark independent findings appear only when an assessment or certificate exists. Category membership does not imply verification.

Methodology · How verification works

Products and providers

Open a product profile for its catalogue details, or use the provider link for the company profile. Claimed listings appear first, then by name. Payment never changes the order.

  • AWS IoT Greengrass

    By Amazon Web Services

    AWS IoT Greengrass is an open-source edge runtime and AWS cloud service for building, deploying and managing software on IoT devices. Developers assemble device software from prebu

  • Ambarella CV3

    By Ambarella

    Ambarella CV3-AD is an ASIL B(D)-compliant AI domain controller system-on-chip family for multi-sensor perception, fusion and path planning in L2+ to L4 autonomous driving and prem

  • Arm AI / Ethos / KleidiAI

    By Arm

    Arm provides CPU/NPU IP and AI software stacks enabling efficient on-device and edge AI inference across mobile and embedded devices. Public marketing also emphasises ubiquitous ed

  • Metis AIPU

    By Axelera AI

    Bring data insights to the edge, increasing the performance of your solutions with a cost-effective and efficient inference chip. Axelera’s AI processing unit is designed to seamle

  • Google Coral

    By Google

    Coral is Google's full-stack platform for edge AI, combining an AI-first, standards-based hardware architecture with a unified developer toolchain so AI can run locally on devices.

  • Graphcore

    By Graphcore

    Graphcore is a Bristol-origin semiconductor company known for Intelligence Processing Units for machine learning. Public materials cover AI compute hardware and software stacks for

  • Hailo-10

    By Hailo

    Explore Hailo’s AI chip for AI on the edge. Use the best-tailored high-performance AI processors for edge device solutions. Hailo-10 is Hailo's hardware product, from Hailo Technol

  • Hugging Face Optimum

    By Hugging Face

    Hugging Face operates a model hub, inference tooling and collaboration products for machine-learning teams. Public pages cover hosting, inference endpoints and open-model distribut

  • Imagination AI GPUs/NPUs IP

    By Imagination

    Imagination Technologies designs GPU/NPU IP for efficient graphics and AI inference in edge and mobile devices. Public marketing also emphasises edge GPU/NPU IP licensing. It is pr

  • ONNX Runtime

    By Microsoft

    ONNX Runtime is Microsoft's open-source, cross-platform engine for speeding up machine learning inference and training in an existing technology stack. It runs models on CPUs, GPUs

  • Mobileye SuperVision

    By Mobileye

    Leading the evolution of automobility from advanced driver-assistance systems to autonomous driving through world-renowned expertise in artificial intelligence. Mobileye SuperVisio

  • Jetson AGX Orin Developer Kit

    By NVIDIA

    The NVIDIA Jetson AGX Orin Developer Kit is a compact edge AI computer for prototyping generative AI, robotics and computer vision products. It delivers up to 275 TOPS from a 2048-

  • Qualcomm AI Engine Direct

    By Qualcomm

    Learn how Qualcomm transforms industries with leading edge AI, high-performance, low-power computing and unrivaled connectivity. Qualcomm AI Engine Direct is Qualcomm's platform, f

  • Galaxy AI

    By Samsung

    Welcome to Samsung UK. Discover a wide range of home electronics with cutting-edge technology including TVs, smartphones, tablets, home appliances & more. Galaxy AI is Samsung's ha

  • SiMa.ai Modalix

    By SiMa.ai

    SiMa.ai scaling physical ai across across robotics, automotive, industrial automation, aerospace & defense, smart vision, and healthcare. SiMa.ai Modalix is SiMa.ai's hardware prod

Products

Claimed products appear first. Ranking packs and payment do not change this list.

Also used in this category

These products have a different primary category so they do not compete for the same ranking queries. They are listed here because buyers still encounter them in this job.

Related categories

Relevant procurement and assurance guides

Frequently asked questions

What is Edge inference?

Running models at the edge (gateways, stores, plants) as an inference product, not embedded chips or on-device assistants. Jobs: store/plant inference; gateway runtimes; fleet of edge nodes.

What should not be listed as Edge inference?

Products whose buyer job is embedded AI, on-device assistants, or GPU cloud inference. Those belong on their own category page so search queries are not split.

Has AI Trustmark independently assessed every Edge inference supplier?

No. A category listing is descriptive. Independent assessment is shown only on company or product pages that carry Trustmark evidence.

What model or provider changes should a buyer insist on being told about?

Material change usually includes a new model family, new region, new subprocessor, new write-capable tool, or a change that affects logging, privacy or human oversight. Those changes should trigger evidence refresh rather than a silent release.

How should buyers verify where AI customer data is processed?

Ask for the named processing locations, cloud regions and any subprocessors that see prompts, files or outputs. A directory listing is not evidence of residency. Independent assessment records the locations that were in scope on the assessment date.

Does a TrustMark on one product cover the rest of the company?

No. Independent assessment is scoped to the named organisation and, where relevant, the named product. Category pages list suppliers as a topic label. They do not imply that every listed company has been assessed.

What incident-handling evidence is useful for AI suppliers?

Buyers should see how AI-specific failures are detected, contained and notified — including unsafe outputs, data leakage and unauthorised agent actions. An incident policy that never mentions models, prompts or tools is incomplete for this class of product.

What security testing evidence should buyers request for an AI product?

Ask what was tested, against which version, whether prompt-injection, data-exfiltration and tenant isolation were in scope, and where failed prompts were stored. A generic ISO certificate or a vendor scanner screenshot is not by itself an AI TrustMark assessment.