Tag: vLLM
-
Local LLM Showdown: Why Qwen 3.6 27B Won My Dual-GPU Setup
After weeks of testing MiniMax 2.5, 2.7, and five coding environments on my dual-GPU workstation, here is why Qwen 3.6 27B became my daily driver.
-
Setting Up and Using Hermes Agent: A Practical Guide
I spent a good chunk of time setting up Hermes Agent for my home lab, and there’s a lot to get right before it becomes genuinely useful. This is my…
-
vLLM vs. LM Studio: Why I Run Both for Local LLMs
With 96GB of VRAM on an RTX Pro 6000, I have plenty of power for local LLMs. Here is why I use LM Studio for discovery and vLLM for production.