Hermes: New FREE Local AI Model
Want to make money and save time with AI? Get AI Coaching, Support & Courses ๐ https://www.skool.com/ai-profit-lab-7462/about
Get the video notes + links to the tools โ https://www.skool.com/ai-profit-lab-7462/about
Get a FREE AI Course + 1000 NEW AI Agents ๐ https://www.skool.com/ai-seo-with-julian-goldie-1553/about
Want to know how I make videos like these? Join the AI Profit Boardroom โ https://www.skool.com/ai-profit-lab-7462/about
Get a FREE AI SEO Strategy Session: https://go.juliangoldie.com/strategy-session?utm=julian
Run a fully private AI agent locally โ no subscriptions, no โฆ
Watch on YouTube โ
(saves to browser)
Chapters (15)
Intro โ Why local AI agents keep failing on consumer hardware
0:21
What Is Carnis Moe 35B A3B โ The free model built for local agents
0:40
Why Most Local Models Break on Agentic Tasks
1:04
MoE Architecture Explained โ 35B params, 3B compute cost
1:52
Performance vs. Larger Models โ Why smarter beats bigger
2:33
What Makes This Fine-Tune Different โ Trained on real agent traces
3:15
Two-Stage Training Breakdown โ How the model learned to act
3:49
VRAM Requirements โ What GPU you actually need
4:32
Hardware & Quantization Guide โ Q4KM to Q8_0 breakdown
5:04
Context Window โ Why 128K matters for long agentic tasks
5:47
Step-by-Step Setup โ Llama.cpp, model download & server config
6:33
Installing Hermes Agent โ Open source, MIT licensed, cross-platform
6:53
What This Agent Can Actually Do โ 40+ tools, memory, autonomous skills
7:41
Bottom Line โ Is Carnis Moe worth running locally?
8:14
Who This Is For โ Private AI setup with no monthly fees
DeepCamp AI