Hermes Agent + Ollama Setup on Windows โ€” Free Local AI Agent with Qwen 3.8

โ—6 โ—17 โ—34
calendar_today ago โ€ข schedule1 min read

๐Ÿค– Build a FREE local AI agent on your Windows PC with Hermes Agent + Ollama + Qwen 3.8. No API key, no subscription, and your files never leave your machine. In this step-by-step Hermes Agent setup tutorial, I install Ollama, download Qwen 3.8, fix the 64K context length error, install Hermes Desktop on Windows, and test it on 3 real tasks.

๐Ÿ“– Full written guide with all commands: https://thecodestreet.dev/post/hermes-agent-ollama-qwen-windows/

โฑ๏ธ Chapters
0:00 Free Local AI Agent Demo on Windows PC
0:15 What is Hermes Agent? (Free & Local AI Agent)
1:08 Hermes vs Ollama vs Qwen: How They Work Together
1:38 Hardware Requirements for Qwen 3.8 27B (VRAM & RAM)
2:31 Best Qwen Model for Your GPU (8GB, 12GB, 16GB, 24GB)
2:48 Step 1: How to Install Ollama on Windows
3:29 Step 2: Download Qwen 3.8 in Ollama
4:17 Why Qwen 3 Doesn't Work with Hermes Agent
4:43 Step 3: Fix Ollama Context Length (64K for Hermes)
6:18 Step 4: Install Hermes Desktop on Windows
7:46 Step 5: Connect Hermes Agent to Ollama + Fix Errors
9:39 Use Case 1: Find Large Files with AI Agent
10:45 Use Case 2: Summarise a PDF Locally with AI
11:50 Use Case 3: Generate a README with AI Agent
12:54 Local AI vs Cloud AI: Honest Verdict
13:43 Hermes Agent + Ollama Common Errors & Fixes
14:23 Outro

๐Ÿ”— Links & Downloads
๐Ÿฆ™ Ollama: https://ollama.com
Hermes Desktop: https://hermes-agent.nousresearch.com/desktop
๐Ÿง  Qwen 3.8 on Ollama: https://ollama.com/library/qwen3.8

๐Ÿ’ป Commands Used
ollama --version
ollama pull qwen3.8:27b
ollama ps

โš™๏ธ Hermes โ†’ Ollama Settings
Base URL: http://localhost:11434
Model: qwen3.8:27b
Context length: 64000
API key: leave empty

๐ŸชŸ Windows 10 Hermes install (PowerShell):
iex (irm https://hermes-agent.nousresearch.com/install.ps1)

๐Ÿ–ฅ๏ธ My Setup
GPU: RTX 4070 (12GB VRAM)
RAM: 32GB
Storage: 1TB SSD
OS: Windows 11

๐ŸŽฏ Which Model Should You Use?
24GB VRAM โ†’ qwen3.8:27b
12โ€“16GB VRAM โ†’ qwen3.5:9b
8GB VRAM โ†’ qwen3.5:4b

๐Ÿ“บ Watch Next
โ–ถ๏ธ What Is Context Size in Ollama? (Qwen 3.8 Explained): https://youtu.be/-_E-3PKpbgQ
โ–ถ๏ธ Claude Code Free with Ollama + Qwen 3.8: https://youtu.be/7GaWpOj9MKs

๐Ÿ’ฌ What would you automate with a free local AI agent? Tell me in the comments!

๐Ÿ‘ If this helped, like the video and subscribe to The Code Street for more free AI, local LLM and AI agent tutorials.

HermesAgent #Ollama #LocalAI

Want more #ai & #llm deep dives?

Join 5,962+ developers sharing real benchmarks, code breakdowns, and projects. Free forever.

Part 9 of 10 in AI

More Posts

Your AI Agent Doesn't Need Your Token: Edera's Ariadne Conill on Object Capabilities

Tom Smithverified - Nov 5

Hermes Agent Telegram Setup on Windows โ€” Control Your Local AI From Phone

TheCodeStreet - Nov 19

AAIF Hits 10 Projects. Its CTO on What to Adopt Now and the Security Gaps Left Open

Tom Smithverified - Oct 23

What Security Teams Want From AI Agents Before They Let Them Act Alone

Tom Smithverified - Nov 18

Architecting a Local-First Hybrid RAG for Finance

Pocket Portfolio - Feb 25
chevron_left
1.5k Points โ€ข 57 Badges
17Posts
4Comments
12Connections
I specialize in designing and developing intelligent systems powered by Microsoft Azure OpenAI, Agen... Show more

Related Jobs

View all jobs โ†’

Commenters (This Week)

1 comment
1 comment

Contribute meaningful comments to climb the leaderboard and earn badges!