Tenstorrent Wormhole™ n150 Series AI Accelerator – 12GB GDDR6 | 262 TFLOPS FP8 | 72 Tensix Cores | 288GB/s | PCIe 4.0

Next-Generation AI Computing Powered by Tenstorrent Wormhole Architecture

Unlock advanced artificial intelligence computing with the Tenstorrent Wormhole™ n150 Series, a high-performance PCIe AI accelerator platform designed for machine learning developers, AI researchers, data scientists, universities, and advanced computing professionals.

Built on Tenstorrent’s innovative Wormhole Tensix architecture, the n150 Series delivers 262 TFLOPS peak FP8 performance, 72 active Tensix processing cores, 12GB GDDR6 memory, 288GB/s memory bandwidth, and PCI Express 4.0 x16 connectivity.

Available in both active-cooled and passive-cooled configurations, the Wormhole n150 Series offers flexible deployment options for compatible desktop workstations and server environments.

Whether 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.

Key Features & Highlights

• 262 TFLOPS FP8 AI Performance – High-throughput low-precision AI processing for supported workloads.
• 72 Active Tensix Cores – Specialized compute cores optimized for tensor operations.
• 12GB GDDR6 Memory – High-speed onboard memory for AI models and computational workloads.
• 288GB/s Memory Bandwidth – Fast data transfer between memory and processing resources.
• 108MB On-Chip SRAM – High-speed local memory supporting efficient tensor processing.
• 74 TFLOPS FP16 Performance – Computational capability for supported higher-precision AI workloads.
• 148 TFLOPS BLOCKFP8 Performance – Specialized block floating-point acceleration.
• PCI Express 4.0 x16 Interface – High-bandwidth workstation and server connectivity.
• 160W Total Board Power – Performance-oriented accelerator with a manageable power envelope.
• 1GHz AI Clock – Dedicated Wormhole processing architecture.
• QSFP-DD Interconnect Ports – Two 200Gbps ports for compatible Wormhole accelerator connections.
• Warp 100 Bridge Support – Additional connectivity for supported multi-card configurations.
• Open-Source Development Tools – Access to Tenstorrent’s AI programming environment.

Powerful Wormhole Tensix Processor Architecture

The Tenstorrent Wormhole n150 Series features a specialized processor architecture developed to accelerate artificial intelligence and machine learning computations.

With 72 active Tensix cores, the accelerator provides dedicated processing resources for neural network operations, matrix computations, and supported tensor-intensive workloads.

The architecture combines programmable processing, high-speed memory, and advanced data movement capabilities.

Advanced AI Computing Performance

The Wormhole n150 delivers the following theoretical peak compute performance:

262 TFLOPS – FP8

Designed for supported low-precision AI computations.

148 TFLOPS – BLOCKFP8

Specialized block floating-point computation for compatible workloads.

74 TFLOPS – FP16

Higher-precision floating-point computation for supported AI applications.

These performance capabilities make the n150 Series suitable for specialized AI development and research.

Peak theoretical performance figures are not equivalent to guaranteed real-world inference or training throughput.

12GB GDDR6 Memory with 288GB/s Bandwidth

The Wormhole n150 Series integrates a high-performance memory architecture.

Memory Highlights

12GB GDDR6 Memory

Provides onboard memory for neural network parameters, intermediate tensors, and computational data.

288GB/s Memory Bandwidth

Supports rapid data movement during supported AI workloads.

192-bit Memory Bus

Enables efficient communication with onboard GDDR6 memory.

108MB On-Chip SRAM

Provides fast local memory resources for Tensix processing operations.

This memory configuration makes the Wormhole n150 particularly useful for AI prototyping, smaller language models, computer vision research, and specialized inference applications.

Two Cooling Options – n150d and n150s

The Tenstorrent Wormhole n150 Series includes two configurations designed for different deployment environments.

Wormhole n150d – Active Cooling

Designed for desktop workstations

The n150d includes an integrated axial-fan cooling solution, making it suitable for compatible desktop AI development systems.

Key advantages:

• Factory-installed active cooling
• Designed for workstation deployment
• 2.5-slot PCIe card form factor
• 12GB GDDR6 memory
• 262 TFLOPS FP8 performance
• 160W total board power

Manufacturer Part Number: TC-02002

Wormhole n150s – Passive Cooling

Designed for server environments

The n150s features a passive heatsink intended for systems providing sufficient forced airflow.

Key advantages:

• Passive heatsink cooling
• Suitable for compatible rack-mounted servers
• Dual-slot PCIe card form factor
• Optional active cooling kit support
• 12GB GDDR6 memory
• 262 TFLOPS FP8 performance
• 160W total board power

Manufacturer Part Number: TC-02001

Important: The n150s requires sufficient forced airflow. For desktop use without adequate chassis cooling, the appropriate Active Cooling Kit is required.

Advanced Multi-Card Connectivity

The Wormhole n150 Series includes dedicated accelerator interconnect capabilities.

Each card features:

• 2 × QSFP-DD 200G active interconnect ports
• 2 × Warp 100 Bridge connection points

These interfaces enable supported connections between compatible Tenstorrent Wormhole accelerators.

Benefits of Accelerator Interconnects

Multi-Card AI Research

Explore compatible multi-accelerator configurations.

High-Speed Communication

Support direct data exchange between compatible Wormhole processors.

Flexible AI Infrastructure

Build development systems with multiple supported accelerator cards.

Distributed Computing Experiments

Investigate specialized parallel computing and AI workload distribution.

The 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.

Applications & Use Cases

1. Artificial Intelligence Development

Develop, test, and optimize supported AI models using Tenstorrent’s software ecosystem.

2. Machine Learning Research

Explore neural networks, tensor processing, and alternative accelerator architectures.

3. Generative AI & Language Models

Experiment with supported small language models, transformer architectures, and AI inference workloads.

4. Computer Vision

Research supported image classification, visual recognition, and object detection applications.

5. Deep Learning Development

Build and evaluate compatible neural network implementations.

6. AI Education & Universities

A specialized platform for students, researchers, and educational institutions studying AI hardware and programming.

7. Custom AI Kernel Programming

Develop and optimize computational kernels using Tenstorrent’s programming tools.

8. Multi-Accelerator Research

Experiment with supported Wormhole interconnect configurations for advanced AI computing.

Complete Technical Specifications

System Requirements

For optimal installation and operation, Tenstorrent specifies the following baseline requirements:

• CPU: x86-64 architecture
• Motherboard: PCI Express 4.0 x16 slot
• System RAM: Minimum 64GB
• Storage: Minimum 100GB, with 2TB or more recommended
• Operating System: Ubuntu 22.04
• Power Connector: One EPS12V 4+4-pin connection
• Expansion Space: Dual-slot for n150s; 2.5-slot for n150d
• Cooling: Adequate chassis airflow
• Internet: Required for software installation

Power Connector Warning: Do not connect a standard 6+2-pin PCIe GPU power cable directly to the card’s EPS12V connector.

Why Choose Tenstorrent Wormhole n150?

1. Dedicated AI Processing Architecture

The Wormhole Tensix processor is designed for specialized artificial intelligence workloads.

2. Powerful FP8 Computing

Up to 262 TFLOPS peak FP8 compute performance for compatible applications.

3. Fast GDDR6 Memory

12GB onboard memory with 288GB/s bandwidth.

4. Flexible Cooling Configurations

Choose active-cooled n150d for desktop systems or passive-cooled n150s for properly ventilated servers.

5. Multi-Card Connectivity

Dedicated Warp 100 and QSFP-DD interfaces support compatible accelerator interconnections.

6. Open-Source Development Environment

Access Tenstorrent’s tools for software development and AI research.

7. Research-Friendly Platform

Suitable for developers and organizations exploring alternatives to conventional GPU computing.

Frequently Asked Questions

Q1. What is the Tenstorrent Wormhole n150?

The Wormhole n150 is a PCIe AI accelerator designed for machine learning, artificial intelligence research, and supported neural network workloads.

Q2. How much memory does the n150 have?

It features 12GB GDDR6 memory with 288GB/s bandwidth.

Q3. How powerful is the Wormhole n150?

It provides 262 TFLOPS FP8, 148 TFLOPS BLOCKFP8, and 74 TFLOPS FP16 theoretical peak performance.

Q4. What is the difference between n150d and n150s?

The n150d uses active axial-fan cooling for desktop workstations, while the n150s uses passive cooling for systems with adequate forced airflow.

Q5. Does the n150 support PCIe 4.0?

Yes. Both versions feature PCI Express 4.0 x16 connectivity.

Q6. Can the n150 run large language models?

It 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.

Q7. Does Wormhole n150 support CUDA?

No. Tenstorrent uses its own software ecosystem rather than NVIDIA CUDA.

Q8. Can multiple Wormhole n150 cards be connected?

Yes, in supported configurations using the appropriate Warp 100 or QSFP-DD interconnect hardware.

Q9. What power connector does the n150 require?

It requires one 4+4-pin EPS12V power connector.

Q10. Is the Wormhole n150 suitable for AI research in India?

Yes. It is a useful option for AI researchers, universities, developers, and organizations experimenting with specialized AI accelerator technology.

Buy Tenstorrent Wormhole n150 Series AI Accelerator in India

Explore 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.

Featuring 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.

Order Now | Request Best Price | Enquire for Availability | Contact for Bulk Orders

Product availability, included accessories, warranty, delivery timelines, and final pricing are subject to confirmation.

Field Recommended value

Vendor Tenstorrent

Product type AI Accelerator Card

Series Wormhole n150

Variants n150d Active / n150s Passive

SKU n150d TC-02002

SKU n150s TC-02001

Category Computer Components / AI Accelerators

Condition New (if applicable)

Advanced 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.

9. Google SEO keywords

Primary keyword: Tenstorrent Wormhole n150 India

Secondary keywords: Buy Tenstorrent Wormhole n150, Wormhole n150 Price India, Tenstorrent n150d, Tenstorrent n150s, 12GB AI Accelerator, 262 TFLOPS AI Card, PCIe 4.0 AI Acce