Agentic AI · AI Agent · Nvidia · GitHub · Blackwell · Llama · NVIDIA Blog
The latest is Hermes Agent, which crossed 140,000 GitHub stars in under three months and, as of last week
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
✓ KHAO Verified
Developed by Nous Research, Hermes is designed for reliability and self-improvement, two qualities that have historically been hard to achieve with agents.
Key facts
- With 128GB of unified memory and 1 petaflop of AI performance, NVIDIA DGX Spark can run 120 billion-parameter mixture-of-experts models all day
- NVIDIA RTX PRO GPUs deliver up to 3x faster token generation running Qwen 3.6 models with llama.cpp
- In addition, Qwen 3.6 27B is a new, dense model with more active parameters, matching the accuracy of 400 billion-parameter models like Qwen 3.5 397B while being one-sixteenth the size
- The latest Qwen 3.6 models build on the acclaimed Qwen 3.5 series to deliver another leap forward for local AI agents
Summary
Agentic AI is changing the way users get work done. Qwen 3.6, a new series of high-performance, open weight large language models (LLMs) from Alibaba, are ideal for running local agents like Hermes. Like other popular agents, Hermes integrates with messaging apps, can access local files and applications, and runs 24/7. Self-Evolving Skills: Hermes writes and refines its own skills.