{"product_id":"tenstorrent-wormhole™-n150-ai-accelerator-12gb-gddr6-262-tflops-72-tensix-cores-pcie-4-0","title":"Tenstorrent Wormhole™ n150 AI Accelerator | 12GB GDDR6 | 262 TFLOPS | 72 Tensix Cores | PCIe 4.0","description":"\u003cp\u003e\u003cspan\u003eTenstorrent Wormhole™ n150 Series AI Accelerator – 12GB GDDR6 | 262 TFLOPS FP8 | 72 Tensix Cores | 288GB\/s | PCIe 4.0\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eNext-Generation AI Computing Powered by Tenstorrent Wormhole Architecture\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eUnlock advanced artificial intelligence computing with the Tenstorrent Wormhole™ n150 Series\u003c\/span\u003e\u003cspan\u003e, a high-performance PCIe AI accelerator platform designed for machine learning developers, AI researchers, data scientists, universities, and advanced computing professionals.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBuilt on Tenstorrent’s innovative Wormhole Tensix architecture, the n150 Series delivers \u003c\/span\u003e\u003cspan\u003e262 TFLOPS peak FP8 performance, 72 active Tensix processing cores, 12GB GDDR6 memory, 288GB\/s memory bandwidth, and PCI Express 4.0 x16 connectivity\u003c\/span\u003e\u003cspan\u003e.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eAvailable in both active-cooled and passive-cooled configurations, the Wormhole n150 Series offers flexible deployment options for compatible desktop workstations and server environments.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWhether you’re developing neural networks, experimenting with generative AI, researching machine learning architectures, or building custom AI computing applications, the Wormhole n150 provides a programmable accelerator platform supported by Tenstorrent’s open-source software ecosystem.\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\u003e262 TFLOPS FP8 AI Performance\u003c\/span\u003e\u003cspan\u003e – High-throughput low-precision AI processing for supported workloads.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e72 Active Tensix Cores\u003c\/span\u003e\u003cspan\u003e – Specialized compute cores optimized for tensor operations.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e12GB GDDR6 Memory\u003c\/span\u003e\u003cspan\u003e – High-speed onboard memory for AI models and computational workloads.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e288GB\/s Memory Bandwidth\u003c\/span\u003e\u003cspan\u003e – Fast data transfer between memory and processing resources.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e108MB On-Chip SRAM\u003c\/span\u003e\u003cspan\u003e – High-speed local memory supporting efficient tensor processing.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e74 TFLOPS FP16 Performance\u003c\/span\u003e\u003cspan\u003e – Computational capability for supported higher-precision AI workloads.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e148 TFLOPS BLOCKFP8 Performance\u003c\/span\u003e\u003cspan\u003e – Specialized block floating-point acceleration.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003ePCI Express 4.0 x16 Interface\u003c\/span\u003e\u003cspan\u003e – High-bandwidth workstation and server connectivity.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e160W Total Board Power\u003c\/span\u003e\u003cspan\u003e – Performance-oriented accelerator with a manageable power envelope.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003e1GHz AI Clock\u003c\/span\u003e\u003cspan\u003e – Dedicated Wormhole processing architecture.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eQSFP-DD Interconnect Ports\u003c\/span\u003e\u003cspan\u003e – Two 200Gbps ports for compatible Wormhole accelerator connections.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eWarp 100 Bridge Support\u003c\/span\u003e\u003cspan\u003e – Additional connectivity for supported multi-card configurations.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eOpen-Source Development Tools\u003c\/span\u003e\u003cspan\u003e – Access to Tenstorrent’s AI programming environment.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003ePowerful Wormhole Tensix Processor Architecture\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Tenstorrent Wormhole n150 Series features a specialized processor architecture developed to accelerate artificial intelligence and machine learning computations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWith 72 active Tensix cores, the accelerator provides dedicated processing resources for neural network operations, matrix computations, and supported tensor-intensive workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe architecture combines programmable processing, high-speed memory, and advanced data movement capabilities.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eAdvanced AI Computing Performance\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Wormhole n150 delivers the following theoretical peak compute performance:\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e262 TFLOPS – FP8\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDesigned for supported low-precision AI computations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e148 TFLOPS – BLOCKFP8\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSpecialized block floating-point computation for compatible workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e74 TFLOPS – FP16\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eHigher-precision floating-point computation for supported AI applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThese performance capabilities make the n150 Series suitable for specialized AI development and research.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003ePeak theoretical performance figures are not equivalent to guaranteed real-world inference or training throughput.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e12GB GDDR6 Memory with 288GB\/s Bandwidth\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Wormhole n150 Series integrates a high-performance memory architecture.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eMemory Highlights\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e12GB GDDR6 Memory\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eProvides onboard memory for neural network parameters, intermediate tensors, and computational data.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e288GB\/s Memory Bandwidth\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSupports rapid data movement during supported AI workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e192-bit Memory Bus\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eEnables efficient communication with onboard GDDR6 memory.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e108MB On-Chip SRAM\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eProvides fast local memory resources for Tensix processing operations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThis memory configuration makes the Wormhole n150 particularly useful for AI prototyping, smaller language models, computer vision research, and specialized inference applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eTwo Cooling Options – n150d and n150s\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Tenstorrent Wormhole n150 Series includes two configurations designed for different deployment environments.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWormhole n150d – Active Cooling\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDesigned for desktop workstations\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe n150d includes an integrated axial-fan cooling solution, making it suitable for compatible desktop AI development systems.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eKey advantages:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cspan\u003eFactory-installed active cooling\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003eDesigned for workstation deployment\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e2.5-slot PCIe card form factor\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e12GB GDDR6 memory\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e262 TFLOPS FP8 performance\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e160W total board power\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003eManufacturer Part Number: TC-02002\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWormhole n150s – Passive Cooling\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDesigned for server environments\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe n150s features a passive heatsink intended for systems providing sufficient forced airflow.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eKey advantages:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cspan\u003ePassive heatsink cooling\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003eSuitable for compatible rack-mounted servers\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003eDual-slot PCIe card form factor\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003eOptional active cooling kit support\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e12GB GDDR6 memory\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e262 TFLOPS FP8 performance\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e160W total board power\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003eManufacturer Part Number: TC-02001\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eImportant:\u003c\/span\u003e\u003cspan\u003e The n150s requires sufficient forced airflow. For desktop use without adequate chassis cooling, the appropriate Active Cooling Kit is required.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eAdvanced Multi-Card Connectivity\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Wormhole n150 Series includes dedicated accelerator interconnect capabilities.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eEach card features:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cspan\u003e2 × QSFP-DD 200G active interconnect ports\u003c\/span\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cspan\u003e2 × Warp 100 Bridge connection points\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003eThese interfaces enable supported connections between compatible Tenstorrent Wormhole accelerators.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBenefits of Accelerator Interconnects\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eMulti-Card AI Research\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExplore compatible multi-accelerator configurations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eHigh-Speed Communication\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSupport direct data exchange between compatible Wormhole processors.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFlexible AI Infrastructure\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBuild development systems with multiple supported accelerator cards.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDistributed Computing Experiments\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eInvestigate specialized parallel computing and AI workload distribution.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe QSFP-DD ports are intended for supported Tenstorrent Wormhole accelerator interconnections, not ordinary Ethernet networking. They should not be confused with the 800G Blackhole P150 interconnect ports.\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, test, and optimize supported AI models using Tenstorrent’s software ecosystem.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e2. Machine Learning Research\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExplore neural networks, tensor processing, and alternative accelerator architectures.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e3. Generative AI \u0026amp; Language Models\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExperiment with supported small language models, transformer architectures, and AI inference workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e4. Computer Vision\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eResearch supported image classification, visual recognition, and object detection applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e5. Deep Learning Development\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBuild and evaluate compatible neural network implementations.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e6. AI Education \u0026amp; Universities\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eA specialized platform for students, researchers, and educational institutions studying AI hardware and programming.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e7. Custom AI Kernel Programming\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDevelop and optimize computational kernels using Tenstorrent’s programming tools.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e8. Multi-Accelerator Research\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExperiment with supported Wormhole interconnect configurations for advanced AI computing.\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\u003eProduct Series\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eWormhole n150\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\u003eModels\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003en150d \/ n150s\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\u003en150d Part Number\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTC-02002\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\u003en150s Part Number\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eTC-02001\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\u003eWormhole 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\u003eWormhole ASICs\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e1\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\u003eActive Tensix Cores\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e72\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\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e1GHz\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\u003eFP8 Performance\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e262 TFLOPS\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\u003eFP16 Performance\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e74 TFLOPS\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\u003eBLOCKFP8 Performance\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e148 TFLOPS\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\u003e12GB 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\u003e192-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\u003e12 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\u003e288GB\/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\u003e108MB\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 4.0 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\u003eQSFP-DD Connectivity\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e2 × 200G\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\u003eBridge Connectivity\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e2 × Warp 100\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\u003e160W\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 Connector\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e1 × EPS12V 4+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\u003en150d Cooling\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eActive Axial Fan\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\u003en150s Cooling\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003ePassive Heatsink\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\u003en150d Dimensions\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e52.2 × 256 × 111mm\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\u003en150s Dimensions\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003e36 × 254 × 111mm\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\u003eOperating System\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd valign=\"middle\"\u003e\n\u003cp\u003e\u003cspan\u003eSupported Linux \/ Ubuntu\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\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp\u003e\u003cspan\u003eSystem Requirements\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFor optimal installation and operation, Tenstorrent specifies the following baseline requirements:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cspan\u003eCPU:\u003c\/span\u003e\u003cspan\u003e x86-64 architecture\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eMotherboard:\u003c\/span\u003e\u003cspan\u003e PCI Express 4.0 x16 slot\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eSystem RAM:\u003c\/span\u003e\u003cspan\u003e Minimum 64GB\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eStorage:\u003c\/span\u003e\u003cspan\u003e Minimum 100GB, with 2TB or more recommended\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eOperating System:\u003c\/span\u003e\u003cspan\u003e Ubuntu 22.04\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003ePower Connector:\u003c\/span\u003e\u003cspan\u003e One EPS12V 4+4-pin connection\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eExpansion Space:\u003c\/span\u003e\u003cspan\u003e Dual-slot for n150s; 2.5-slot for n150d\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eCooling:\u003c\/span\u003e\u003cspan\u003e Adequate chassis airflow\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan\u003eInternet:\u003c\/span\u003e\u003cspan\u003e Required for software installation\u003c\/span\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003ePower Connector Warning:\u003c\/span\u003e\u003cspan\u003e Do not connect a standard 6+2-pin PCIe GPU power cable directly to the card’s EPS12V connector.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eWhy Choose Tenstorrent Wormhole n150?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e1. Dedicated AI Processing Architecture\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Wormhole Tensix processor is designed for specialized artificial intelligence workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e2. Powerful FP8 Computing\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eUp to 262 TFLOPS peak FP8 compute performance for compatible applications.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e3. Fast GDDR6 Memory\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e12GB onboard memory with 288GB\/s bandwidth.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e4. Flexible Cooling Configurations\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eChoose active-cooled n150d for desktop systems or passive-cooled n150s for properly ventilated servers.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e5. Multi-Card Connectivity\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eDedicated Warp 100 and QSFP-DD interfaces support compatible accelerator interconnections.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e6. Open-Source Development Environment\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eAccess Tenstorrent’s tools for software development and AI research.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e7. Research-Friendly Platform\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSuitable for developers and organizations exploring alternatives to conventional GPU computing.\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 Wormhole n150?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe Wormhole n150 is a PCIe AI accelerator designed for machine learning, artificial intelligence research, and supported neural network workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ2. How much memory does the n150 have?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt features 12GB GDDR6 memory with 288GB\/s bandwidth.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ3. How powerful is the Wormhole n150?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt provides 262 TFLOPS FP8, 148 TFLOPS BLOCKFP8, and 74 TFLOPS FP16 theoretical peak performance.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ4. What is the difference between n150d and n150s?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eThe n150d uses active axial-fan cooling for desktop workstations, while the n150s uses passive cooling for systems with adequate forced airflow.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ5. Does the n150 support PCIe 4.0?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eYes. Both versions feature PCI Express 4.0 x16 connectivity.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ6. Can the n150 run large language models?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt supports compatible language model workloads. Its 12GB onboard memory makes it more appropriate for smaller models and development experiments than very large models requiring substantial accelerator memory.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ7. Does Wormhole n150 support CUDA?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eNo. Tenstorrent uses its own software ecosystem rather than NVIDIA CUDA.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ8. Can multiple Wormhole n150 cards be connected?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eYes, in supported configurations using the appropriate Warp 100 or QSFP-DD interconnect hardware.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ9. What power connector does the n150 require?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eIt requires one 4+4-pin EPS12V power connector.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eQ10. Is the Wormhole n150 suitable for AI research in India?\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eYes. It is a useful option for AI researchers, universities, developers, and organizations experimenting with specialized AI accelerator technology.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eBuy Tenstorrent Wormhole n150 Series AI Accelerator in India\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eExplore next-generation AI computing with the Tenstorrent Wormhole n150 Series – an advanced AI accelerator platform designed for machine learning, deep learning, neural network research, and AI software development.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eFeaturing 12GB GDDR6 memory, 262 TFLOPS FP8 performance, 72 Tensix cores, PCIe 4.0 connectivity, and dedicated accelerator interconnects, the Wormhole n150 offers a flexible solution for specialized AI computing.\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, included accessories, warranty, delivery timelines, and final pricing are subject to confirmation.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eField\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eRecommended value\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eVendor\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eTenstorrent\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eProduct type\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eAI Accelerator Card\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSeries\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eWormhole n150\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eVariants\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003en150d Active \/ n150s Passive\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSKU n150d\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eTC-02002\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSKU n150s\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eTC-02001\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eCategory\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eComputer Components \/ AI Accelerators\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eCondition\u003c\/span\u003e\u003cspan\u003e \u003c\/span\u003e\u003cspan\u003eNew (if applicable)\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eAdvanced PCIe 4.0 AI accelerator featuring 72 Tensix cores, 12GB GDDR6 memory, 288GB\/s bandwidth, 262 TFLOPS FP8 performance, and 160W board power. Available in active-cooled n150d and passive-cooled n150s versions for compatible AI workstations and servers.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003e9. Google SEO keywords\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003ePrimary keyword:\u003c\/span\u003e\u003cspan\u003e Tenstorrent Wormhole n150 India\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eSecondary keywords:\u003c\/span\u003e\u003cspan\u003e Buy Tenstorrent Wormhole n150, Wormhole n150 Price India, Tenstorrent n150d, Tenstorrent n150s, 12GB AI Accelerator, 262 TFLOPS AI Card, PCIe 4.0 AI Acce\u003c\/span\u003e\u003c\/p\u003e","brand":"DealCliq.com","offers":[{"title":"N 150d Active cooling","offer_id":68074502488363,"sku":null,"price":199999.0,"currency_code":"INR","in_stock":true},{"title":"N 150s Passive cooling","offer_id":68074502521131,"sku":null,"price":189999.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0705\/8240\/3371\/files\/IMG_3267.png?v=1794396359","url":"https:\/\/dealcliq.com\/products\/tenstorrent-wormhole%e2%84%a2-n150-ai-accelerator-12gb-gddr6-262-tflops-72-tensix-cores-pcie-4-0","provider":"DealCliq.com","version":"1.0","type":"link"}