Tenstorrent TT-QuietBox 2 Launched: A RISC-V Powered AI Workstation With 128 GB GDDR6 Memory, Liquid-Cooling & $9999 Starting Price

Tenstorrent has unveiled its TT-QuietBox 2 AI Workstation, powered by the RISC-V architecture, featuring liquid cooling & 128 GB of VRAM for $9999.

Tenstorrent Makes Its Own Liquid-Cooled & Fully RISC-V Powered AI Workstation With The Ability To Run 120B Models With Ease

The Tenstorrent TT-QuietBox 2 is an AI workstation designed to fulfill the needs of AI enterprises and customers. It features the company's Blackhole AIC, which is powered by 16 big RISC-V cores & pack up to 32 GB of GDDR6 memory. The QuietBox 2 is configured with up to four of these Blackhole cards and up to 128 GB of GDDR6 memory. That is in addition to the 256 GB of system memory that is onboard the workstation. While this workstation is developed by Tenstorrent itself, the company is also working with Razer on a separate AI accelerator device that packs the Wormhole AI chip.

Press Release: Tenstorrent, the AI computing company led by CEO Jim Keller, today announced TT-QuietBox 2 (Blackhole). This whisper-quiet, liquid-cooled AI workstation runs models up to 120 billion parameters directly at your desk, ships with an entirely open-source software stack from compiler to kernel, and starts at $9,999. It marks the industry's first desktop AI workstation built on the RISC-V architecture, delivering teraflop-class inference.

The Inference Imperative

QuietBox 2 is built around a different proposition: developers doing the actual work of AI should be able to see, control, and own every layer of their compute, from silicon architecture to the compiler. It is ideal for developers and small-to-medium business deployments requiring on-prem deployment without racks.

Real Workloads Out of the Box

QuietBox 2 ships ready for quick deployment. It excels across diverse AI domains:

• LLMs & Coding: GPT-OSS 120B runs entirely on-device — a full 120-billion-parameter model operating privately at your desk. Llama 3.1 70B runs at 476.5 tokens per second. Qwen3-32B deploys as a private coding agent, reasoning through entire codebases without cloud token limits.
• Creative & Multimodal: Flux handles image generation, and Wan 2.2 handles video synthesis entirely locally, ensuring creative IP remains off third-party servers.
• Scientific Research: Boltz-2, a biomolecular ML model, predicts the structure of a 686-amino-acid protein in just 49 seconds on a single Blackhole processor — a task that takes a modern CPU 45 minutes. This matches the performance of flagship workstation GPUs at a fraction of the cost. QuietBox 2 can predict four protein structures in parallel, yielding 4x higher throughput.

For models not on the pre-installed list, TT-Forge — Tenstorrent’s open-source AI compiler — can run models from PyTorch, ONNX, TensorFlow, JAX, and PaddlePaddle directly to the hardware. If it runs on a standard framework, it can run on QuietBox 2.

Silicon Innovation Without Memory + Networking Bottlenecks

Four Blackhole ASICs work as a unified mesh inside a single desk-friendly enclosure. The system features 480 Tensix cores delivering 2,654 TFLOPS at BlockFP8 precision, backed by 128 GB of GDDR6 high-speed memory and 256 GB of DDR5 system memory.

This architecture integrates compute and high-density SRAM on a single die. This dataflow approach moves tensors efficiently through on-chip memory, completely sidestepping the DRAM bottlenecks that limit sustained throughput on conventional hardware. By utilizing GDDR6 and on-chip SRAM, QuietBox 2 entirely avoids the High-Bandwidth Memory (HBM) supply shortages currently driving price hikes across the rest of the AI hardware market.

The system runs on Ubuntu 24.04, plugs into a standard 120V wall outlet, and requires no rack, specialized electrical work, or server room.

Open Source at Every Layer

Every layer of QuietBox 2's software is open source. This is not just an open API on a black box; it is full-stack visibility.

• TT-Forge gives developers total visibility into graph lowering, transformation, optimization, and execution.
• TT-Metalium, the low-level AI SDK, provides kernel-level control with deterministic execution.
• TT-LLK handles low-level kernel software

Developers can see exactly what happens at every stage of their pipeline, debug at the hardware level, fork any component, and modify the stack to fit their exact workload. For sovereign AI deployments, regulated industries, and research institutions that must guarantee how their infrastructure handles data, this transparency is not just a feature — it is the core architecture.

A Fun Developer Experience

QuietBox 2 represents a ground-up redesign focused on developer velocity and environmental efficiency. The system ships fully pre-configured with Ubuntu 24.04, the complete open-source software stack, and TT-Studio, enabling quick deployment right out of the box.

Engineering advancements have reduced idle power consumption and heat output by approximately 50% compared to previous generations. Coupled with significantly expanded documentation and developer tooling, the new liquid-cooled chassis is engineered specifically for quiet, sustained, heavy-workload operation directly on a desk.

Availability: TT-QuietBox 2 ships globally in Q2 2026, starting at $9,999. To join the waitlist, visit www.tenstorrent.com/waitlist/tt-quietbox.

Follow Wccftech on Google to get more of our news coverage in your feeds.