Solution Blueprint Catalog

Solution Blueprint Catalog#

The Solution Blueprint catalog ranges from simple demos and basic interfaces to fully-fledged agentic platforms and development environments. The catalog is constantly expanded to showcase the cutting edge innovations and to cover the established AI use cases.

Solution Blueprints are designed to run on AMD Instinct, Radeon, and EPYC. Browse the catalog below to find blueprints for your use case.

ROCm version

Solution Blueprints are tested with ROCm 7.2.3.

Blueprint

Description

AIMs

Resources

Agentic RAG (MCP)

Decoupled RAG blueprint with an MCP Knowledge Server and an agentic UI client.

GPT OSS 20B, Embedding

2 GPU, 13 CPU, 272 GiB RAM

Agentic Testing

AI-powered UI testing with an LLM agent that interprets specs, automates browser tests, and generates CI-ready test code.

GPT OSS 120B

1 GPU, 8 CPU, 72 GiB RAM

Agentic Translation

Multi-agent translation workflow where LLM agents critique and refine outputs to improve translation quality.

Llama 3.3 70B

1 GPU, 5 CPU, 68 GiB RAM

AutoGen Studio Agentic Platform

No-code visual platform to design, test, and deploy agentic AI workflows with language models and tools.

Llama 3.3 70B

1 GPU, 6 CPU, 68 GiB RAM

Code Docs Builder

Agentic documentation assistant that analyzes repositories and generates structured software architecture and component docs.

Llama 3.3 70B

1 GPU, 4 CPU, 64 GiB RAM

Continue.dev Coding Assistant

Browser-based AI pair programmer with a local LLM for code completion, fixes, and interactive coding support.

Qwen 3 32B, Qwen 2 5 Coder 7B

3 GPU, 12 CPU, 256 GiB RAM

Document Summarization

Multimodal summarization service for text, PDF, DOCX, audio, and video content.

Llama 3.3 70B, Whisper

1 GPU, 5 CPU, 65 GiB RAM

FinTech Onboarding

KYC onboarding workflow for fintech customer verification.

Mistral Small 3 2 24B 2506

2 GPU, 4 CPU, 64 GiB RAM

Financial Stock Intelligence

Financial analysis assistant combining stock data, technical indicators, and LLM reasoning for market insights.

Llama 3.3 70B

1 GPU, 5 CPU, 68 GiB RAM

LLM Chat Sandbox

Sandbox chat interface to test prompts, evaluate outputs, and understand LLM behavior before production use.

Llama 3.1 8B

1 GPU, 5 CPU, 68 GiB RAM

LLM Router

Prompt router that classifies requests and sends them to the best LLM endpoint using configurable routing rules.

Llama 3.1 8B, Llama 3.3 70B, Embedding

1 GPU, 4 CPU, 192 GiB RAM

Med Assist Voice Consultation

LiveKit-based voice consultation app with agent backend, web UI, and LLM support for medical assistance.

Llama 3.3 70B, Qwen ASR

2 GPU, 16 CPU, 132 GiB RAM

MRI Analysis Tool

MRI analysis tool with a Gradio interface and LLM-generated reports.

GPT OSS 20B

1 GPU, 5 CPU, 68 GiB RAM

PDF to Podcast

End-to-end pipeline that turns PDF documents into podcast-style audio using agentic orchestration, LLMs, and TTS.

Llama 3.3 70B, Qwen TTS

2 GPU, 16 CPU, 104 GiB RAM

Preventative Healthcare Application

Multi-agent preventive healthcare outreach system that identifies screening candidates and drafts personalized emails.

Llama 3.3 70B

1 GPU, 5 CPU, 68 GiB RAM

Report Generation Engine

Multi-stage LLM engine that performs web research and produces structured, citation-backed technical reports.

Llama 3.3 70B

1 GPU, 2 CPU, 68 GiB RAM

Talk to Your Documents

RAG application for chatting with documents using ChromaDB retrieval and LLM-based answers.

Llama 3.3 70B, Embedding

2 GPU, 11 CPU, 268 GiB RAM

Telecom Assistant

Real-time telecom voice assistant for customer support, account actions, and ticketing workflows.

GPT OSS 120B, Mistral Small 3 2 24B 2506, Embedding, Qwen ASR, Qwen TTS

5 GPU, 34 CPU, 421 GiB RAM

Blueprint

Description

AIMs

Resources

Agentic RAG (MCP)

Decoupled RAG blueprint with an MCP Knowledge Server and an agentic UI client.

Qwen 3 Vl 8B, Embedding

2 GPU, 13 CPU, 80 GiB RAM

Agentic Testing

AI-powered UI testing with an LLM agent that interprets specs, automates browser tests, and generates CI-ready test code.

Qwen 3 Vl 8B

1 GPU, 8 CPU, 40 GiB RAM

Agentic Translation

Multi-agent translation workflow where LLM agents critique and refine outputs to improve translation quality.

Qwen 3 Vl 8B

1 GPU, 5 CPU, 36 GiB RAM

AutoGen Studio Agentic Platform

No-code visual platform to design, test, and deploy agentic AI workflows with language models and tools.

Qwen 3 Vl 8B

1 GPU, 6 CPU, 36 GiB RAM

Document Summarization

Multimodal summarization service for text, PDF, DOCX, audio, and video content.

Qwen 3 Vl 8B, Whisper

1 GPU, 5 CPU, 33 GiB RAM

FinTech Onboarding

KYC onboarding workflow for fintech customer verification.

Qwen 3 Vl 8B

2 GPU, 4 CPU, 32 GiB RAM

Financial Stock Intelligence

Financial analysis assistant combining stock data, technical indicators, and LLM reasoning for market insights.

Qwen 3 Vl 8B

1 GPU, 5 CPU, 36 GiB RAM

LLM Chat Sandbox

Sandbox chat interface to test prompts, evaluate outputs, and understand LLM behavior before production use.

Qwen 3 Vl 8B

1 GPU, 5 CPU, 36 GiB RAM

LLM Router

Prompt router that classifies requests and sends them to the best LLM endpoint using configurable routing rules.

Llama 3.1 8B, Qwen 3 Vl 8B, Embedding

1 GPU, 4 CPU, 32 GiB RAM

Med Assist Voice Consultation

LiveKit-based voice consultation app with agent backend, web UI, and LLM support for medical assistance.

Qwen 3 Vl 8B, Qwen ASR

2 GPU, 16 CPU, 100 GiB RAM

MRI Analysis Tool

MRI analysis tool with a Gradio interface and LLM-generated reports.

Qwen 3 Vl 8B

1 GPU, 5 CPU, 36 GiB RAM

PDF to Podcast

End-to-end pipeline that turns PDF documents into podcast-style audio using agentic orchestration, LLMs, and TTS.

Qwen 3 Vl 8B, Qwen TTS

2 GPU, 16 CPU, 72 GiB RAM

Preventative Healthcare Application

Multi-agent preventive healthcare outreach system that identifies screening candidates and drafts personalized emails.

Qwen 3 Vl 8B

1 GPU, 5 CPU, 36 GiB RAM

Report Generation Engine

Multi-stage LLM engine that performs web research and produces structured, citation-backed technical reports.

Qwen 3 Vl 8B

1 GPU, 2 CPU, 36 GiB RAM

Talk to Your Documents

RAG application for chatting with documents using ChromaDB retrieval and LLM-based answers.

Qwen 3 Vl 8B, Embedding

2 GPU, 11 CPU, 76 GiB RAM

Blueprint

Description

AIMs

Resources

Code Docs Builder

Agentic documentation assistant that analyzes repositories and generates structured software architecture and component docs.

Llama 3.1 8B

188 CPU, 128 GiB RAM

Document Summarization

Multimodal summarization service for text, PDF, DOCX, audio, and video content.

Llama 3.1 8B, Whisper

189 CPU, 129 GiB RAM

Financial Stock Intelligence

Financial analysis assistant combining stock data, technical indicators, and LLM reasoning for market insights.

Llama 3.1 8B

189 CPU, 132 GiB RAM

LLM Chat Sandbox

Sandbox chat interface to test prompts, evaluate outputs, and understand LLM behavior before production use.

Llama 3.1 8B

189 CPU, 132 GiB RAM

Report Generation Engine

Multi-stage LLM engine that performs web research and produces structured, citation-backed technical reports.

Llama 3.1 8B

189 CPU, 132 GiB RAM

Talk to Your Documents

RAG application for chatting with documents using ChromaDB retrieval and LLM-based answers.

Llama 3.1 8B, Embedding

223 CPU, 172 GiB RAM

Resources are example values, and can be reduced or increased depending on the user’s requirements.

Blueprint

Description

AIMs

Resources

Desktop Agent Gateway

A self-contained, fully open-source secure gateway for coding agents that runs entirely on one machine

Qwen3-Coder-30B, AXIS, Lemonade SDK, GAIA

Strix Halo Ryzen AI, 128 GiB RAM