Company comparison

Mythic vs FuriosaAI

Radar profile, momentum bars, and stack placement side by side.

← Back to Compare

Mythic
Not scored
momentum
FuriosaAI
Not scored
momentum
Mythic capital
—
FuriosaAI capital
—
No radar series.

Momentum head-to-head

    Attribute tape

    FieldMythicFuriosaAI
    CategorySemiconductors and hardwareSemiconductors and hardware
    StackLayer 1Layer 1
    HQAustin, TX, United StatesSeoul, South Korea
    Founded20122017
    StatusOperatingOperating
    Funding——
    Momentum——
    SummaryMythic builds analog compute-in-memory AI processors (Analog Processing Units) for edge inference, enabling GPU-class performance at a fraction of the power. Its APU platform stores model weights as analog conductance values and executes multiply-accumulate operations in the analog domain for applications including surveillance, robotics, drones, and machine vision.FuriosaAI is a South Korean fabless semiconductor company that designs AI inference accelerators (NPUs) for data-center workloads, including large language models and computer vision. Its hardware-software co-design approach — anchored by the proprietary Tensor Contraction Processor (TCP) architecture and RNGD accelerator family — targets high performance per watt and per dollar as an alternative to GPU-centric AI infrastructure.
    Who forTeams evaluating AI vendors in this category.Teams evaluating AI vendors in this category.
    DifferentiatorMythic builds analog compute-in-memory AI processors (Analog Processing Units) for edge inference, enabling GPU-class performance at a fraction of the power. Its APU platform stores model weights as analog conductance values and executes multiply-accumulate operations in the analog domain for applications including surveillance, robotics, drones, and machine vision.FuriosaAI is a South Korean fabless semiconductor company that designs AI inference accelerators (NPUs) for data-center workloads, including large language models and computer vision. Its hardware-software co-design approach — anchored by the proprietary Tensor Contraction Processor (TCP) architecture and RNGD accelerator family — targets high performance per watt and per dollar as an alternative to GPU-centric AI infrastructure.
    Open MythicOpen FuriosaAI