CiMicro.ai

CIMTech is a Georgia Tech spinout (Prof. Shimeng Yu's lab) designing compute-in-memory AI memory chips and inference racks that let datacenter operators support more users and longer context within the same power budget; Georgia Tech's Feb 2026 release also framed it as a radiation-tolerant, energy-efficient AI processor for edge and space platforms.

Founded in 2012 and based in Palo Alto, develops analog in-memory computing chips for AI inference.

Undisclosed · $125M · 2025-12

Niobium (Niobium Microsystems, Inc.) was spun out of cryptography firm Galois in 2021 and is headquartered in Dayton, Ohio. It builds purpose-built hardware accelerators for fully homomorphic encryption (FHE), positioned as 'zero trust computing' that lets data be computed in the cloud without decryption, and co-founded the FHE hardware consortium FHETCH.

$6M

Weina Hexin (MicroNano CoreChip), founded in 2021 in Hangzhou, China, develops and mass-produces edge-side and AIoT compute-in-memory AI chips based on its proprietary 3D-CIM™ architecture.

Series C · $154M · 2026-09

Qianhe Yibang was established in 2024 and incubated by NetEase. It is one of the earliest Chinese companies focusing on 3D in-memory computing, 3D integrated native chip architecture, and cloud gaming acceleration. The core team has been researching chips based on 3D DRAM in-memory computing architecture since 2018, achieving deep integration of computing and storage through 3D space stacking, breaking through the limitations of the von Neumann architecture. NetEase Youdao and China Mobile are long-term shareholders. In 2025, it reached a strategic cooperation with Tencent Cloud. In August 2026 it closed a Series B of over 2 billion yuan, with investors including the National Adjustment Fund, the China Mobile Chain Leader Fund and other institutions.

Series B · 2026-08

Reexen Technology (九天睿芯), founded in 2018 in Shenzhen, develops neuromorphic compute-in-memory chips that integrate sensing, storage, and computation using brain-inspired analog-digital hybrid architectures.

Series B · $29M · 2026-04

Fractile, founded in 2022 in London, UK, develops advanced AI chips that run AI models 100x faster than traditional methods at 10x lower cost.

Series B · $236M · 2026-05

Olix, founded in 2024 in London, develops photonic AI chips targeting inference workloads to reduce high-bandwidth memory constraints.

Series B · $532M · 2026-08 · Valuation $3.3B

Ubitium, founded in 2023 in Düsseldorf, Germany, develops a universal RISC-V microprocessor capable of handling various computing tasks including AI without the need for dedicated chips.

Seed · $18M · 2026-10

Founded in 2020 in Seongnam, South Korea, Rebellions designs energy-efficient AI inference chips.

Pre-IPO · $898M · 2026-03 · Valuation $2.3B

Founded in 2021 in Tel Aviv, QuamCore designs superconducting quantum processor architectures that embed digital control logic within the cryogenic chamber, targeting integration of one million qubits within a single cryostat.

Series A · $34M · 2025-08

Spun out of SenseTime's large chip division and independently established in Hangzhou in 2025, Sunrise focuses on developing and commercializing AI inference GPUs and multimodal inference chips, with its flagship S1/S2 products already in mass production.

Undisclosed · $582M · 2026-04 · Valuation $1.5B