Company comparison
Untether AI vs FuriosaAI
Radar profile, momentum bars, and stack placement side by side.
Untether AI
Not scored
momentum
FuriosaAI
Not scored
momentum
Untether AI capital
—
FuriosaAI capital
—
No radar series.
Momentum head-to-head
Attribute tape
| Field | Untether AI | FuriosaAI |
|---|---|---|
| Category | Semiconductors and hardware | Semiconductors and hardware |
| Stack | Layer 1 | Layer 1 |
| HQ | Toronto, Ontario, Canada | Seoul, South Korea |
| Founded | 2018 | 2017 |
| Status | Acquired | Operating |
| Funding | — | — |
| Momentum | — | — |
| Summary | Untether AI built energy-centric AI inference accelerator chips using an at-memory compute architecture designed to minimize data movement and power consumption for neural-network workloads at the edge and in the cloud. The engineering team was acqui-hired by AMD circa mid-2025. | 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 for | Teams evaluating AI vendors in this category. | Teams evaluating AI vendors in this category. |
| Differentiator | Untether AI built energy-centric AI inference accelerator chips using an at-memory compute architecture designed to minimize data movement and power consumption for neural-network workloads at the edge and in the cloud. The engineering team was acqui-hired by AMD circa mid-2025. | 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. |
