---
title: "AI300"
url: "https://www.qualcomm.com/data-center/products/qualcomm-dragonfly-ai300"
description: "Qualcomm Dragonfly AI300: rack-level AI inference platform with HBC Gen2 for scalable, power-efficient hyperscale generative AI deployments."
canonicalUrl: "https://www.qualcomm.com/data-center/products/qualcomm-dragonfly-ai300"
---

# AI300

Active

Qualcomm Dragonfly™

[Contact Sales](https://www.qualcomm.com/support/contact/forms/data-center)

Save to Workspace

![chip image](https://s7d1.scene7.com/is/image/dmqualcommprod/Dragonfly_AI300_Raster_RGB_Color?fmt=webp-alpha&qlt=85)

On this page

[Overview](https://www.qualcomm.com/#overview)

[Benefits](https://www.qualcomm.com/#benefits)

[Features / Specs](https://www.qualcomm.com/#features)

Third-generation, rack-level AI inference platform integrating our next-gen near-memory computing with increased bandwidth scale-up and scale-out, designed for disaggregated inference deployments

Qualcomm Dragonfly™ AI300 expands the Qualcomm Dragonfly AI inference offering by integrating [Qualcomm® Hign Bandwidth Compute (HBC) Gen 2](https://www.qualcomm.com/data-center/expertise/ai-accelerators), enabling full all-to-all rack level scale-up, and high bandwidth scale-out to support full disaggregated inferencing deployments. The solution will expand from a rack to a pod offering supporting the entire inference pipeline and enables fast deployment.

Built for hyperscale AI, it is designed for industry-leading¹ memory capacity and effective bandwidth enabling high-throughput, low-latency performance for large language & multimodal model(LMM, LMM) inference and agentic AI workloads.

Product license agreement

## Benefits

- **Industry-leading Perf/TCO for LLM Decode¹**
AI300 with HBC Gen 2 is designed for industry-leading memory capacity and effective memory bandwidth, offering the right balance to efficiently service large context attention as well as large model feed forward networks (FFN).

- **Standardized Pod Configurations**
AI300 fully validated pod configurations enable the capability to run end-end inference pipelines in a self contained unit of deployment

- **AI Inference Software**
Expands our AI inference capabilities to deliver seamless disaggregated inference solutions across Qualcomm Technologies and other vendor hardware.

- **Power-efficient Inference**
Qualcomm HBC with near-memory computing architecture reduces data movement — the dominant source of energy consumption in inference — increasing tokens-per-watt.

- **Holistic co-designed System Solution**
Custom CPU, AI accelerator, connectivity, software, and algorithms are developed simultaneously from the ground up for AI inference.

¹Compared to competing published product specifications normalized at card- and rack-level.

## Features

- AI300 accelerator cards with fully integrated compute, memory and networking on a single direct liquid cooled (DLC) rack
- Integrated Qualcomm HBC Gen 2 is engineered for industry-leading effective memory bandwidth ¹
- All-to-all rack scale-up with a single hop to enable high bi-directional bandwidth per AI300 accelerator
- Qualcomm Dragonfly™ C1000 CPU delivers high per core performance for accelerating agentic AI use-cases
- Expanded scale-out per AI300 card to enable low latency full prefill-decode disaggregation at scale
- Fully validated pod configurations to enable complete end-end inference solution for customers
- Air and direct liquid cooling

QUALCOMM DRAGONFLY AI INFRASTRUCTURE MANAGEMENT SUITE

Orchestrate and
scale efficiency

The suite provides provisioning, monitoring, orchestration and fault handling across rack‑scale deployments. Together, hardware, connectivity and software form the foundation of a cohesive data center platform approach — one designed to scale with customers as AI workloads evolve.

[Learn more](https://www.qualcomm.com/data-center/solutions/ai-infrastructure-management-suite)