DeepFellow DOCS

Architecture

DeepFellow Server

DeepFellow Server is the gateway to access MCP servers, Tools, DeepFellow Infra, Plugins, and Vector Data Base (VDB). It also provides authorization and administration layers to the system. It is also used for user and access management, business logic and all the other application-related operations.

Your DeepFellow Server should have at least 1 CPU and 2GB RAM.

DeepFellow Architecture – self-hosted infra, DeepFellow Server, MCPs, tools, OpenAI API and client interfaces

DeepFellow Infra

DeepFellow Infra is a self-hosted infrastructure, a physical stack that holds the computing power for AI models to work. Home for the LLM's, embedding models, and MLA's.

DeepFellow example specification with sample hardware and its estimated costs

Example Infra Specification and Cost

CardIcon

1. Server Solutions: Large models, good performance

  • 160GB VRAM, 256GB RAM
  • 8×4000 ADA 20GB, Intel Xenon

Estimated cost:

  • base: 3 000-16 000 USD
  • graphic cards: 2 000-60 000 USD

CardIcon

2. PC Workstation: Small and medium models at large speed

  • 32-128GB RAM
  • 2×Nvidia GPU

Estimated cost:

  • base: 1 000-3 000 USD
  • consumer graphic cards: 1 000-6 000 USD

CardIcon

3. Mac Studio: Large models at moderate speed

  • 35-512GB RAM
  • 14-32 CPU, 32-80 GPU, 16-32 Neural

Estimated cost:

  • base: 3 000-25 000 USD

CardIcon

4. MacBook Pro: Medium models at low speed

  • 36-128GB RAM
  • 14-16 CPU, 32-40 GPU, 16 Neural

Estimated cost:

  • base: 2 000-10 000 USD

We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.