Build My Rig
AI Workflow

Basic Coding Assistant

basic

Run a single local coding model for code completion and chat. The entry-level builder setup: replace API-dependent code completion with a local 7-8B model.

CursorContinueLM StudioOllama

Concurrent VRAM

5.8 GB

Peak VRAM

5.8 GB

Min Bandwidth

200 GB/s

Models

1

Memory

VRAM Breakdown

How the 5.8 GB concurrent VRAM is used.

Switched (Loaded As Needed)

These share VRAM with the largest concurrent model. Only one runs at a time.

Llama 3.1 8B Instruct(code completion and chat)
5.8 GB

Q5_K_M

Return on Investment

Local vs API Costs

Typical Monthly API Cost

$30/mo

Break-Even Point

25 months

Annual Savings

~$288/yr

Based on ~200 Cursor completions/day at ~$1/day API cost. Budget AI Desktop at $753. Privacy and offline access are the main value drivers at this tier, not pure cost savings.

Hardware

Recommended Builds

Pre-configured builds that can run the Basic Coding Assistant workflow.

Budget

Budget AI Desktop

Your own AI coding setup for under $800

RTX 3060 12GB·12 GBVRAM

Runs 7 models

$684

Prefer a Mac? Apple Silicon with unified memory can run this workflow too. See the Mac AI Builder workflow →

Build my rig for this workflow →