Aiserver Manufacturer
1 / 5
| Product Introduction | TianGai 150 (Model: MR-V150-64-00) is a general-purpose GPU accelerator card focused on AI inference, scientific computing, and video encoding/decoding. Built on a self-developed architecture with high computing power, large memory, and low power consumption. |
| Model Name | TianGai 150 |
| Benchmark Product | Comparable to 4090 or V100 |
| INT8 Performance | 660 TOPS |
| FP16 Performance | 147 TFLOPS |
| FP32 Performance | 37 TFLOPS |
| VRAM Type | HBM2E (High Bandwidth Memory, approx. 30% higher bandwidth compared to HBM2) |
| Fabrication Process | TSMC 7nm FinFET with 2.5D CoWoS advanced packaging |
| DirectX Support | Compatible with DirectX 12 (including 12_1 features) |
| Memory Frequency | Effective frequency 4000MHz (800GB/s bandwidth) |
| Memory Bus Width | 4096-bit |
| Memory Speed | 0.5 ns |
| Interface Type | PCIe Gen4.0 x16 (bidirectional bandwidth 64GB/s) |
| Form Factor | FHFL dual-slot |
| Weight | 1064g |
Cyber Resilient Architecture for Zero Trust IT environment
Security is integrated into every phase of the lifecycle, including protected supply chain and factory-to-site integrity assurance. Silicon-based root of trust anchors end-to-end boot resilience.
Increase efficiency and accelerate operations with autonomous collaboration
The systems management portfolio delivers a secure, efficient, and comprehensive solution for servers. Simplify, automate and centralize management with advanced enterprise consoles.
Eco-friendly Design
Designed for energy efficiency to help reduce the carbon footprint and lower operation costs. We ensure innovative options for energy efficiency throughout the product portfolio.
Designed for 24x7 enterprise data center operations, featuring enterprise-grade components and hardware optimized for deployment at scale.
Supports Secure Boot with Hardware Root of Trust technology, meeting NEBS Level 3 standards. The passively cooled, dual-socket design is easy to integrate into existing data center infrastructure.
