Unverified50% confidenceFactExact time
Maia 300 is equipped with 8 HBM4 memory stacks, uses compute chiplets manufactured on TSMC's N2P process, and is deployed in the form of 96-accelerator racks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedHigh-end AI accelerators such as the NVIDIA H100 integrate HBM370% similarUnverified英伟达H100/H200 GPU每颗封装5~6个HBM3e堆栈70% similarUnverified英伟达H100/H200 GPU均依赖CoWoS将计算芯片与HBM3内存集成，CoWoS产能瓶颈一度制约了H100的整体供货量66% similarUnverifiedNVIDIA's B200 is based on the Blackwell architecture, manufactured using TSMC's 4NP process, consists of two dies coupled via a 10 TB/s chip-to-chip interconnect, and contains a total of 208 billion transistors.66% similarUnverifiedThe H100 is based on the Hopper architecture, contains 80 billion transistors, and can deliver approximately 4 petaFLOPS of FP8 compute per card.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1027332API
curl https://kongchang.com/api/v1/knowledge/claims/1027332MCP
get_claim(id=1027332)