Company comparison
Samsung Foundry vs FuriosaAI
Radar profile, momentum bars, and stack placement side by side.
Samsung Foundry
Not scored
momentum
FuriosaAI
Not scored
momentum
Samsung Foundry capital
—
FuriosaAI capital
—
No radar series.
Momentum head-to-head
Attribute tape
| Field | Samsung Foundry | FuriosaAI |
|---|---|---|
| Category | Semiconductors and hardware | Semiconductors and hardware |
| Stack | Layer 1 | Layer 1 |
| HQ | Hwaseong, Gyeonggi-do, South Korea | Seoul, South Korea |
| Founded | — | 2017 |
| Status | Operating | Operating |
| Funding | — | — |
| Momentum | — | — |
| Summary | Samsung Foundry is the contract chip manufacturing and advanced packaging division of Samsung Electronics, producing custom semiconductors for AI, HPC, mobile, automotive, and IoT customers. It offers end-to-end AI silicon enablement through process technology, chiplet integration, and heterogeneous packaging under a one-stop turnkey model. | 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 | Samsung Foundry is the contract chip manufacturing and advanced packaging division of Samsung Electronics, producing custom semiconductors for AI, HPC, mobile, automotive, and IoT customers. It offers end-to-end AI silicon enablement through process technology, chiplet integration, and heterogeneous packaging under a one-stop turnkey model. | 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. |
