@vmiss33: I installed Hermes Agent on Windows, and set it up with GPT 5.5. I gave it one of @above_spec's amazing twitter threads…
Summary
The user shares a report on successfully running the Qwen3.6 35B A3B model on Windows using Hermes Agent and an 8GB VRAM GPU.
View Cached Full Text
Cached at: 05/13/26, 12:19 PM
I installed Hermes Agent on Windows, and set it up with GPT 5.5. I gave it one of @above_spec’s amazing twitter threads on Qwen3.6 35B A3B model running on 8GB of VRAM and told it to get it working annnnd… @NousResearch https://t.co/yPNJDptR9m
Similar Articles
@svpino: Hermes with Gemma 4 or Qwen 3.5 is literally the best combo you can run locally on your computer. You've got to give th…
Developer claims Hermes fine-tunes of Gemma 4 and Qwen 3.5 deliver the best local LLM performance, suggesting they rival paid BigAI models.
@sudoingX: this is a laptop running a 31b parameter model at 99% gpu autonomously through hermes agent, 15 tok/s sustained, 22.8 o…
A 31B parameter model runs locally on a laptop via Hermes agent at 15 tok/s, using 22.8 GB VRAM and 94 W power, highlighting fully autonomous, private AI inference without cloud dependencies.
@gregisenberg: how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes v…
Hermes is a personal AI agent that runs in the terminal, featuring built-in memory and 40+ tools, with mobile support and comparisons to OpenClaw.
@zeroxkyle: Over the weekend I set up the Hermes agent, and basically force fed it every resource I could find on X to upgrade it. …
A user reports training a Hermes agent on X resources and ranking them for explanations.
@NousResearch: Computer use with any model Hermes Agent × @trycua
NousResearch announces that their Hermes model can now be used for computer use tasks in combination with the trycua framework.