[email protected]
Home > Domestic graphics > Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
1 / 5
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration
Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration

Large Model Pre-training 64GB HBM2E High-speed Video Memory Fan-Cooled Desktop New Graphics Card PCIe Gen4 Training Acceleration

Send Inquiry

Product Description

TianGai 150 Front view
TianGai 150 Details
Product Specifications
Product Introduction: Tianshu Zhixin TianGai 150 (Model: MR-V150-64-00) is a domestically produced general-purpose GPU accelerator card focused on AI inference, scientific computing, and video encoding/decoding. It is built on a self-developed general architecture, with core specifications designed around 'high computing power, large memory, low power consumption, and wide compatibility.'
Name Tianshu Zhixin TianGai 150
Benchmark product Comparable to 4090 or V100
INT8 660 TOPS
FP16 147 TFLOPS
FP32 37 TFLOPS
VRAM type HBM2E (High Bandwidth Memory, with approximately 30% higher bandwidth compared to HBM2, suitable for the high bandwidth demands of large model inference)
Chip fabrication process TSMC 7nm FinFET process, paired with 2.5D CoWoS advanced packaging (ensuring core heat dissipation and signal stability)
DirectX support Compatible with DirectX 12 (including 12_1 features), suitable for mainstream graphics rendering and video processing scenarios
Video memory frequency Effective frequency 4000MHz (native high-frequency characteristics of HBM2E, achieving low-latency data transfer with 800GB/s bandwidth)
Memory Bus Width 4096-bit (HBM2E standard bus width design, providing sufficient data channels for 32GB VRAM to avoid bandwidth bottlenecks)
Video memory speed 0.5 ns (based on the physical characteristics of HBM2E memory chips, corresponding to an equivalent frequency of 4000 MHz, with latency better than GDDR6)
Output Interface No traditional video output interfaces (DP/HDMI/VGA), focused on data center inference/computing scenarios
Output interface type The core interface is PCIe Gen4.0 x16 (bidirectional bandwidth 64GB/s), supporting x86/ARM host interconnection.
Form Factor FHFL dual-slot
Weight 1064g
Key System Features
Cyber Resilient Architecture
Cyber Resilient Architecture
Security is integrated into every phase of the hardware lifecycle, including protected supply chain and factory-to-site integrity assurance. Silicon-based root of trust anchors end-to-end boot resilience while Multi-Factor Authentication (MFA) and role-based access controls ensure trusted operations.
Autonomous Collaboration
Autonomous Collaboration
Delivers a secure, efficient, and comprehensive solution for servers. Simplify, automate and centralize one-to-many management with the advanced management consoles and integrated remote access controllers.
Sustainability
Sustainability
From recycled materials in products and packaging, to thoughtful, innovative options for energy efficiency, the design is made to deliver and recycle products to help reduce the carbon footprint and lower operation costs.
Enterprise Data Center Operations
TianGai 150 Operations
Designed for 24x7 enterprise data center operations, it features enterprise-grade components and energy-efficient hardware optimized for deployment at scale.

Supports Secure Boot with Hardware Root of Trust technology, provides an extra layer of security, and meets NEBS Level 3 standards to meet new data center standards.

The passively cooled, energy-efficient, dual-socket design fits a wide range of systems from OEM vendors and is easy to integrate into existing data center infrastructure.
Product Component Gallery
Architecture diagram
GPU Core Structure
Board Design
Hardware interface
Cooling Architecture
System compatibility
Full Product Layout
Frequently Asked Questions
What are the core workloads targeted by the Tianshu Zhixin TianGai 150?
The TianGai 150 general-purpose GPU accelerator card is specifically designed for artificial intelligence (AI) inference, high-performance scientific computing, and enterprise-grade video encoding and decoding applications.
What are the performance capabilities of the TianGai 150 GPU?
It delivers outstanding computing performance, offering up to 660 TOPS at INT8, 147 TFLOPS at FP16, and 37 TFLOPS at FP32. Its real-world performance benchmarks are highly comparable to industry standards like the 4090 or V100.
What are the VRAM specifications and bandwidth of this graphics card?
The card utilizes 32GB HBM2E (High Bandwidth Memory) with a 4096-bit memory bus width and a 0.5 ns speed. This configuration achieves an effective frequency of 4000MHz and a total bandwidth of 800GB/s, eliminating traditional memory bottlenecks during large AI model inferences.
Does the TianGai 150 support display output?
No, the card does not feature traditional video output interfaces (such as DP, HDMI, or VGA). It is dedicated strictly to compute-focused tasks in servers and data centers, communicating via a high-speed PCIe Gen4.0 x16 interface.
What packaging and hardware interfaces are used for system integration?
It utilizes the TSMC 7nm FinFET process paired with 2.5D CoWoS advanced packaging to maintain signal integrity and heat dissipation. The physical form factor is a standard FHFL dual-slot card weighing 1064g, using a PCIe Gen4.0 x16 interface that supports both x86 and ARM host interconnections.
What is the typical product lead time and packaging configuration?
Product packages are typically delivered using secure cartons or custom requirements. The delivery time depends on order quantities, usually averaging around 7 days.

Related Products

Brand New In-stock Domestic GPU Acceleration Card, Tianshu Zhixin Zhikai V100 32GB, Comparable to 4090 or V100

Brand New In-stock Domestic GPU Acceleration Card, Tianshu Zhixin Zhikai V100 32GB, Comparable to 4090 or V100
Brand New In-stock Domestic GPU Acceleration Card, Tianshu Zhixin Zhikai V50 16GB, Comparable to T4

Brand New In-stock Domestic GPU Acceleration Card, Tianshu Zhixin Zhikai V50 16GB, Comparable to T4
Brand New Muxixi Si N260 MXN260 64GB HBM2e GPU Graphics Card Fan Cooler PCIe Gen4.0 7nm Workstation Desktop AI Inference Large

Brand New Muxixi Si N260 MXN260 64GB HBM2e GPU Graphics Card Fan Cooler PCIe Gen4.0 7nm Workstation Desktop AI Inference Large
Brand New In-stock Domestic GPU Comparable to A10, AItraining and Inferenceacceleration Kunlun Chip GR800 32GB GPU Graphics Card

Brand New In-stock Domestic GPU Comparable to A10, AItraining and Inferenceacceleration Kunlun Chip GR800 32GB GPU Graphics Card
Brand New In-stock Domestic GPU Comparable to A10, AItraining and Inferenceacceleration KunlunChip R200-8F 32GB GPU GraphicsCard

Brand New In-stock Domestic GPU Comparable to A10, AItraining and Inferenceacceleration KunlunChip R200-8F 32GB GPU GraphicsCard
Brand New In-stock Domestic GPU Acceleration Graphics Card,Tianshu Zhixin TianGai 150/BI-V150 64G

Brand New In-stock Domestic GPU Acceleration Graphics Card,Tianshu Zhixin TianGai 150/BI-V150 64G
Brand New In-stock Domestic GPU Acceleration Graphics Card Tianshu Zhixin TianGai 100/BI-V100 32G HBM2E PCIe Gen4.0 7nm Desktop

Brand New In-stock Domestic GPU Acceleration Graphics Card Tianshu Zhixin TianGai 100/BI-V100 32G HBM2E PCIe Gen4.0 7nm Desktop
Brand New In-stock Domestic GPU Acceleration Graphics Card,Tianshu Zhixin TianGai 150S/BI-V150S 64G

Brand New In-stock Domestic GPU Acceleration Graphics Card,Tianshu Zhixin TianGai 150S/BI-V150S 64G
Brand New in Stock Domestic GPU, Large Model AI Inference, Deep Learning High-performance Graphics Card, Muxi Xiyun C500 64G

Brand New in Stock Domestic GPU, Large Model AI Inference, Deep Learning High-performance Graphics Card, Muxi Xiyun C500 64G
Brand New in Stock Domestic GPU, Large Model AI Inference, Deep Learning High-performance Graphics Card, Muxi Xiyun C550 64G

Brand New in Stock Domestic GPU, Large Model AI Inference, Deep Learning High-performance Graphics Card, Muxi Xiyun C550 64G