Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Tenstorrent’s partnership with Japan’s Rapidus is a development effort linking Tenstorrent’s RISC-V, chiplet and AI-accelerator technology with Rapidus’s planned 2nm logic manufacturing. Japan’s LSTC later selected Tenstorrent IP for an edge-AI accelerator project, with Rapidus involved. The announcements establish an active Japanese development roadmap—not a commercially shipped Tenstorrent-Rapidus chip.
What is the Tenstorrent-Rapidus partnership?
Announced on November 16, 2023 by Tenstorrent and November 17 by Rapidus, the partnership is for joint IP development for AI edge devices based on 2nm logic. It is about developing and integrating semiconductor technology, not launching a finished consumer device. (Sources: Tenstorrent, “Rapidus and Tenstorrent Partner to Accelerate Development of AI Edge Device Domain Based on 2nm Logic,” November 16, 2023; Rapidus, “Rapidus and Tenstorrent Agree to Joint IP Partnership,” November 17, 2023.)
Tenstorrent’s role
Tenstorrent brings RISC-V CPU technology, chiplet design and AI-accelerator architectures. The company’s contribution is the computing design and IP relationship for the planned edge-AI work.
The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Rapidus’s role
Rapidus is developing advanced logic semiconductor technology, including its planned 2nm process, and is responsible for manufacturing-related work. The agreement connects the companies’ design and process-development efforts; it does not by itself establish that a Tenstorrent design has been manufactured at scale.
#1 Best Overall
- Professional AI & Creator Workstation: AMD Radeon AI PRO R9700 GPU with 32GB GDDR6 is engineered for AI development, professional content creation, and compute-intensive workloads.
- Massive 32GB Memory Capacity: 32GB of GDDR6 memory on a 256-bit bus provides ample bandwidth for large AI models, 8K video editing, and complex 3D rendering.
- Advanced RDNA 4 with AI Accelerators: 64 Compute Units with 3rd Gen Ray Tracing and dedicated 2nd Gen AI Accelerators for groundbreaking AI performance and visual computing.
- Professional Blower Cooling: Efficient single blower design exhausts heat directly out of the chassis, ideal for multi-GPU workstation and server configurations.
- Enterprise-Grade Thermal Solution: Vapor chamber heatsink with industrial Honeywell PTM7950 thermal interface material ensures reliable cooling under sustained professional loads.
What is being developed, and who selected Tenstorrent’s IP?
On February 27, 2024, Tenstorrent announced that Japan’s Leading-edge Semiconductor Technology Center (LSTC) selected its RISC-V and chiplet IP for an edge 2nm AI accelerator. Tenstorrent said it would collaborate with Rapidus on the project. This is a concrete project selection within the broader partnership, rather than evidence of a finished chip or a commercial product launch. (Source: Tenstorrent, “Tenstorrent RISC-V and Chiplet Technology Selected to Build the Future of AI in Japan,” February 27, 2024.)
The intended use is edge computing: AI processing closer to the devices and systems using it, rather than only in large data centers. Japan’s Ministry of Economy, Trade and Industry (METI) described the wider Rapidus-Tenstorrent effort as an integrated semiconductor-and-software project, with applications such as robotics. The material identifies an intended direction, not a confirmed deployment in a particular robot or other product. (Source: Japan METI, Rapidus–Tenstorrent MOC strategy material, November 16, 2023.)
Rank #2
- NVIDIA Volta GV100 Architecture — 4,608 CUDA Cores, 640 1st-Gen Tensor Cores delivering 14 TFLOPS FP32 and 112 TFLOPS deep learning performance for AI training, inference, HPC, and scientific computing workloads
- 32GB HBM2 ECC Memory — 900 GB/s Bandwidth — High-bandwidth memory on a 4096-bit bus with ECC error correction provides the memory capacity and throughput required for the largest AI models, simulations, and datasets
- PCIe 3.0 x16 Interface — 250W TDP — Standard PCIe Gen3 connectivity with passive cooling designed for enterprise rack server deployment in HPE ProLiant, Dell PowerEdge, and Supermicro platforms with adequate chassis airflow
- NVLink — Scale to 96GB Unified Memory — Connect two V100 GPUs via NVLink at 300 GB/s bi-directional bandwidth to scale GPU memory from 32GB to 96GB for larger AI training and HPC workloads
- Multi-Precision Computing — Supports FP64 (7 TFLOPS), FP32 (14 TFLOPS), FP16 (112 TFLOPS) and INT8 precision modes for flexible deployment across training, inference, and scientific simulation workloads
Why does the partnership signal momentum in Japan?
The evidence is more substantial than a single agreement: it includes the 2023 IP-development partnership, the 2024 LSTC selection, continuing work with Rapidus, and a Japan engineering-training project commissioned by Japan’s New Energy and Industrial Technology Development Organization (NEDO), recorded in Tenstorrent’s newsroom archive. These activities indicate a growing Japanese presence and development program; they do not establish production volume or commercial sales.
Tenstorrent Chief Customer Officer David Bennett described the company’s broader regional position this way: “We have tremendous momentum with our customers in the Asia Pacific region right now, and I am proud that we can start talking about all the things we are doing in Japan.” The statement is Tenstorrent’s characterization of its customer momentum; the Japan projects above provide specific examples of its activity there. (Source: Tenstorrent/Rapidus partnership announcement.)
Rank #3
- Built for Running LLMs Locally: RDNA 4, 128 AI Accelerators, up to 1,531 TOPS (INT4) for fast inference and fine-tuning
- 32GB GDDR6 VRAM for Large AI Models: 256-bit, up to 640GB/s bandwidth, run large language and multi-modal AI models without offloading
- Multi-GPU Scaling for Local AI Clusters: PCIe 5.0 and 2-slot design support dense multi-GPU builds for local AI training and inference clusters
- Diecast Shroud and Backplate: Wave-pattern design cuts memory temperature by up to 16%, keeping clocks steady during long AI training runs
- Phase-Change GPU Thermal Pad: Delivers superior thermal conductivity for consistent performance and longevity under heavy AI loads
What is Rapidus’s 2nm manufacturing status?
Rapidus has reported process-development milestones, but those milestones should be distinguished from production of a Tenstorrent-designed chip. The company’s original schedule and its later reported progress are:
| Milestone | What was announced or reported | What it establishes |
|---|---|---|
| IIM-1 pilot line | Rapidus said in 2023 that pilot-line operation was targeted for April 2025. | A target date, not confirmation in the cited material that pilot operation began then. |
| 2nm transistor prototypes and equipment | In July 2025, Rapidus reported successful prototyping of 2nm gate-all-around (GAA) transistors and said more than 200 advanced semiconductor-equipment tools had been connected by June 2025. | Reported process-development and facility milestones, not proof of a Tenstorrent chip in volume production. |
| Process design kit | Rapidus said in July 2025 that it intended to release its 2nm process design kit to advance customers in Q1 2026. | A stated target. The cited announcement does not confirm whether the kit was released. |
| Mass production | Rapidus announced a 2027 mass-production target in 2023. | A company target, not a guarantee or confirmation that mass production has begun. |
(Sources: Rapidus, “Rapidus Achieves Significant Milestone at its State-of-the-Art Foundry with Prototyping of Leading-Edge 2nm GAA Transistors,” July 18, 2025; Rapidus, “Rapidus and Tenstorrent Agree to Joint IP Partnership,” November 17, 2023.)
Rank #4
- 24GB GDDR7 ECC Memory: handles large AI, 3D and rendering files smoothly
- Powerful CUDA Compute - 8,960 CUDA cores for fast graphics and computing power
- AI & Ray Tracing Boost - Tensor of the 5th generation and RT cores of the 4th generation
- PCIe 5.0 x16 interface - fast data connection with modern systems
- 4 × DisplayPort 2.1 - Multi-monitor support for professional workflows
The evidence cited here does not give a commercial shipment date for a Tenstorrent-Rapidus chip, a yield figure, a performance benchmark or revenue from the partnership. A process milestone at Rapidus and selection of Tenstorrent IP are meaningful steps, but neither alone answers when a finished product will be available.
Can you buy a Tenstorrent-Rapidus 2nm accelerator?
No commercial Tenstorrent-Rapidus 2nm accelerator is established by the cited announcements. Tenstorrent’s newsroom records the launch of Wormhole-based developer kits and workstations in July 2024, but those developer products should not be confused with a chip made through the Rapidus partnership. Current stock, regional availability and any Amazon listing were not verified.
For a buyer, the key distinction is between existing Tenstorrent developer hardware and the future-facing Japan IP and manufacturing program. Buying a Wormhole developer kit does not provide access to a Rapidus 2nm chip. (Source: Tenstorrent newsroom archive, including its July 18, 2024 Wormhole developer-kit announcement.)
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
