{"product_id":"tenstorrent-blackhole-p150a-ai-accelerator-card-32gb-gddr6-risc-v-architecture-high-performance-ai-computing","title":"Tenstorrent Blackhole P150a AI Accelerator Card | 32GB GDDR6 | RISC-V Architecture | High-Performance AI Computing","description":"\u003cp\u003e\u003cspan\u003eTenstorrent Blackhole P150a AI Accelerator – 32GB GDDR6 | 664 TFLOPS | 120 Tensix Cores | 512GB\/s | PCIe 5.0\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eNext-Generation High-Performance AI Computing with Multi-Card Scalability\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExperience powerful artificial intelligence acceleration with the Tenstorrent Blackhole P150a\u003c\/span\u003e\u003cspan\u003e, an advanced PCIe 5.0 AI accelerator engineered for AI developers, machine learning researchers, data scientists, and high-performance computing professionals.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003ePowered by Tenstorrent’s Blackhole architecture, the P150a combines \u003c\/span\u003e\u003cspan\u003e120 Tensix AI cores, 16 SiFive X280 RISC-V processor cores, 32GB GDDR6 memory, 512GB\/s memory bandwidth, and up to 664 TFLOPS BLOCKFP8 computing performance\u003c\/span\u003e\u003cspan\u003e.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eUnlike conventional AI accelerator cards designed exclusively for standalone operation, the Blackhole P150a features \u003c\/span\u003e\u003cspan\u003efour 800Gbps QSFP-DD interconnect ports\u003c\/span\u003e\u003cspan\u003e, enabling multiple compatible Tenstorrent Blackhole accelerators to communicate directly.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWhether you’re developing advanced neural networks, experimenting with generative AI, building AI research workstations, or exploring scalable machine learning infrastructure, the Blackhole P150a provides a powerful and flexible hardware platform.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eKey Features \u0026amp; Highlights\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cspan\u003e664 TFLOPS BLOCKFP8 AI Performance\u003c\/span\u003e\u003cspan\u003e – High-throughput tensor computing for supported AI workloads.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e120 Tensix Processing Cores\u003c\/span\u003e\u003cspan\u003e – Specialized architecture designed for efficient AI acceleration.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e16 SiFive X280 RISC-V Cores\u003c\/span\u003e\u003cspan\u003e – Programmable processor architecture for advanced computing.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e32GB GDDR6 Memory\u003c\/span\u003e\u003cspan\u003e – High-capacity onboard memory for AI models and data-intensive applications.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e512GB\/s Memory Bandwidth\u003c\/span\u003e\u003cspan\u003e – Rapid memory access for demanding AI processing tasks.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e180MB On-Chip SRAM\u003c\/span\u003e\u003cspan\u003e – Fast local memory for efficient data movement.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003ePCI Express 5.0 x16 Interface\u003c\/span\u003e\u003cspan\u003e – High-speed connectivity with compatible workstations.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e4 × QSFP-DD 800Gbps Ports\u003c\/span\u003e\u003cspan\u003e – Dedicated high-bandwidth links for compatible Blackhole accelerators.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eUp to 1.35GHz AI Clock\u003c\/span\u003e\u003cspan\u003e – High-performance Blackhole processor architecture.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e300W Total Board Power\u003c\/span\u003e\u003cspan\u003e – Performance-focused AI accelerator design.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eActive Blower-Style Cooling\u003c\/span\u003e\u003cspan\u003e – Designed for installation in compatible desktop workstations.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eOpen-Source Software Stack\u003c\/span\u003e\u003cspan\u003e – Developer access to Tenstorrent’s software and programming tools.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003eAdvanced Blackhole AI Processor Architecture\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Tenstorrent Blackhole P150a uses a specialized processor architecture designed to efficiently execute tensor operations and support modern artificial intelligence applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIts \u003c\/span\u003e\u003cspan\u003e120 Tensix cores\u003c\/span\u003e\u003cspan\u003e provide dedicated computational resources for supported neural network operations, while its integrated RISC-V cores enable programmable processing capabilities.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe architecture combines high-performance computation, fast onboard memory, and dedicated interconnect technology to support advanced AI development.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e664 TFLOPS of AI Computing Power\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWith up to \u003c\/span\u003e\u003cspan\u003e664 trillion floating-point operations per second in BLOCKFP8 format\u003c\/span\u003e\u003cspan\u003e, the Blackhole P150a offers substantial theoretical compute throughput for compatible low-precision AI workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThis makes it an attractive option for researchers exploring neural networks, transformer-based models, and specialized machine learning applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe 664 TFLOPS figure represents peak theoretical BLOCKFP8 performance, not guaranteed real-world application throughput.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e32GB GDDR6 Memory with 512GB\/s Bandwidth\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eMemory performance is essential for modern artificial intelligence applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Blackhole P150a features:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cspan\u003e32GB GDDR6 onboard memory\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e512GB\/s memory bandwidth\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e256-bit memory bus\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e16 GT\/s memory speed\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e180MB on-chip SRAM\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003eThis high-bandwidth memory architecture supports rapid movement of model parameters, tensors, and intermediate data during supported AI operations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe 32GB memory capacity also provides additional flexibility for larger models compared with the 28GB Blackhole P100a.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eMulti-Card AI Computing with 800Gbps QSFP-DD Connectivity\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eOne of the most important advantages of the \u003c\/span\u003e\u003cspan\u003eTenstorrent Blackhole P150a\u003c\/span\u003e\u003cspan\u003e is its dedicated high-speed interconnect capability.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe accelerator features \u003c\/span\u003e\u003cspan\u003efour passive QSFP-DD ports, each providing 800Gbps connectivity\u003c\/span\u003e\u003cspan\u003e.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThese interfaces allow compatible Tenstorrent Blackhole P150a and P150b cards to communicate directly, supporting scalable multi-accelerator configurations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBenefits of Multi-Card Connectivity\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eScalable AI Infrastructure\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eConnect compatible Blackhole accelerators to build more powerful multi-card AI development environments.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExpanded Aggregate Memory\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eMultiple interconnected accelerators provide additional distributed memory capacity for supported workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eHigh-Speed Accelerator Communication\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDedicated 800Gbps interfaces support high-bandwidth communication between compatible Blackhole cards.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFlexible Research Configurations\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDevelopers can experiment with distributed AI workloads and multi-device computing architectures.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQSFP-DD connectivity is intended for supported Tenstorrent Blackhole accelerator interconnections. It is not a standard Ethernet networking interface. Appropriate cables, compatible software, and supported topology are required.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eApplications \u0026amp; Use Cases\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e1. Artificial Intelligence Development\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDevelop and experiment with modern AI applications using Tenstorrent’s open-source software ecosystem.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e2. Large Language Models \u0026amp; Generative AI\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExplore supported transformer architectures, language model inference, and generative AI applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e3. Deep Learning \u0026amp; Neural Networks\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBuild and optimize supported neural network applications involving tensor operations and parallel computation.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e4. Computer Vision \u0026amp; Image Processing\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eResearch supported image classification, object detection, visual recognition, and AI-assisted image processing workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e5. AI Research Laboratories\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eAn excellent platform for universities, research organizations, engineering institutions, and AI innovation laboratories.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e6. Multi-Accelerator AI Workstations\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eCreate scalable AI development configurations by connecting compatible Blackhole accelerators through dedicated QSFP-DD interconnects.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e7. Custom AI Kernel Development\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExplore low-level AI programming and optimize specialized computational kernels using Tenstorrent’s software tools.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eComplete Technical Specifications\u003c\/span\u003e\u003c\/p\u003e\n\u003ctable width=\"964.0\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eSpecification\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eDetails\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eManufacturer\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTenstorrent\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eModel\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eBlackhole P150a\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eManufacturer Part Number\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTC-03003\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eProduct Type\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eAI Accelerator Card\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eArchitecture\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eBlackhole Tensix\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTensix Cores\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e120\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eRISC-V Cores\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e16 SiFive X280\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eAI Clock Speed\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eUp to 1.35GHz\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003ePeak AI Compute\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e664 TFLOPS BLOCKFP8\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eOnboard Memory\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e32GB GDDR6\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eMemory Bus\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e256-bit\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eMemory Speed\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e16 GT\/s\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eMemory Bandwidth\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e512GB\/s\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eOn-Chip SRAM\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e180MB\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eHost Interface\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003ePCI Express 5.0 x16\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eInterconnect\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e4 × QSFP-DD 800Gbps\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTotal Board Power\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e300W\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eIdle Power\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eApproximately 75W\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eExternal Power\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e12V-2x6, 12+4-pin\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003ePSU Requirement\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eATX 3.1 certified or better\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eCooling\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eActive blower-style\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eCard Dimensions\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e42 × 270 × 111 mm\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eSoftware\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTenstorrent Open-Source Stack\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eIntended Platform\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eCompatible Desktop Workstations\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp\u003e\u003cspan\u003eSystem Requirements \u0026amp; Compatibility\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFor proper installation and operation, users should prepare a compatible workstation with:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cspan\u003eCPU:\u003c\/span\u003e\u003cspan\u003e Compatible x86-64 host processor\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eMotherboard:\u003c\/span\u003e\u003cspan\u003e PCIe 5.0 x16 slot recommended\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eSystem Memory:\u003c\/span\u003e\u003cspan\u003e At least 64GB recommended for development\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eStorage:\u003c\/span\u003e\u003cspan\u003e Sufficient SSD space for software, models, and datasets\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eOperating System:\u003c\/span\u003e\u003cspan\u003e Supported Linux environment, including compatible Ubuntu releases\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003ePower Supply:\u003c\/span\u003e\u003cspan\u003e ATX 3.1 certified or better\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eExternal Power:\u003c\/span\u003e\u003cspan\u003e Compatible 12V-2x6 power connector\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eCooling:\u003c\/span\u003e\u003cspan\u003e Adequate workstation ventilation\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eExpansion Space:\u003c\/span\u003e\u003cspan\u003e Dual-slot physical clearance\u003c\/span\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003eFor multi-card installations, verify motherboard slot spacing, system power capacity, interconnect cables, and software support.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWhy Choose the Tenstorrent Blackhole P150a?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e1. Powerful AI Processing\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWith 664 TFLOPS peak BLOCKFP8 compute performance, the P150a is designed for demanding AI development workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e2. Larger 32GB Memory\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe additional onboard memory compared with the P100a offers greater flexibility for memory-intensive applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e3. Scalable Multi-Card Architecture\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFour dedicated QSFP-DD ports enable supported multi-accelerator configurations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e4. Open-Source Development\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eTenstorrent provides an open-source programming environment for researchers and developers.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e5. Advanced RISC-V Architecture\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe combination of Tensix cores and RISC-V processors offers a distinctive approach to artificial intelligence computing.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e6. Workstation-Friendly Design\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe active-cooled PCIe form factor allows installation in compatible desktop systems without requiring a dedicated rack-mounted server.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFrequently Asked Questions\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ1. What is the Tenstorrent Blackhole P150a?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe P150a is a high-performance PCIe AI accelerator designed for artificial intelligence development, machine learning, neural network research, and multi-card computing.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ2. How much memory does the Blackhole P150a have?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt includes 32GB GDDR6 memory with 512GB\/s memory bandwidth.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ3. How powerful is the Blackhole P150a?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt provides up to 664 TFLOPS of theoretical BLOCKFP8 compute performance.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ4. What is the difference between Blackhole P100a and P150a?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe P150a offers 32GB GDDR6 instead of 28GB, higher memory bandwidth, and four dedicated 800Gbps QSFP-DD interconnect ports for multi-card configurations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ5. Can multiple P150a cards work together?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eYes. Compatible Blackhole P150a and P150b accelerators can be interconnected using supported QSFP-DD cables and software configurations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ6. Does the Blackhole P150a support CUDA?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eNo. It uses Tenstorrent’s own software ecosystem and is not a drop-in replacement for NVIDIA CUDA hardware.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ7. Is the P150a suitable for large language models?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt supports compatible AI and language model workloads. Actual model compatibility depends on available memory, software implementation, precision, and multi-card configuration.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ8. Can the P150a be installed in a desktop PC?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eYes, provided the workstation meets the physical, electrical, cooling, and software requirements.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ9. Does the P150a include active cooling?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eYes. The P150a includes active blower-style cooling. The P150b is the passive-cooled alternative intended for appropriately cooled server environments.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBuy Tenstorrent Blackhole P150a AI Accelerator in India\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eUpgrade your AI development infrastructure with the Tenstorrent Blackhole P150a – a powerful, scalable AI accelerator designed for next-generation computing.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFeaturing 32GB GDDR6 memory, 664 TFLOPS peak BLOCKFP8 performance, PCIe 5.0 connectivity, and dedicated 800Gbps multi-card interconnects, the P150a is an excellent choice for specialized AI research and development.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eOrder Now | Request Best Price | Enquire for Availability | Contact for Bulk Orders\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eProduct availability, delivery timelines, warranty, and final pricing are subject to seller confirmation.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSEO keywords\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003ePrimary keyword:\u003c\/span\u003e\u003cspan\u003e Tenstorrent Blackhole P150a India\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSecondary keywords:\u003c\/span\u003e\u003cspan\u003e Buy Tenstorrent P150a India, Blackhole P150a 32GB Price, Tenstorrent AI Accelerator India, 664 TFLOPS AI Card, RISC-V AI Processor, PCIe 5.0 AI Accelerator, 32GB AI Computing Card, Tenstorrent Blackhole GPU Alternative, AI Research Hardware India.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e","brand":"DealCliq.com","offers":[{"title":"Default Title","offer_id":68073654026539,"sku":null,"price":269999.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0705\/8240\/3371\/files\/IMG_3263.png?v=1794395402","url":"https:\/\/dealcliq.com\/products\/tenstorrent-blackhole-p150a-ai-accelerator-card-32gb-gddr6-risc-v-architecture-high-performance-ai-computing","provider":"DealCliq.com","version":"1.0","type":"link"}