Posts

Running Local LLMs

Image
Its been a while since I’ve had a topic in technology that I felt strongly enough to write about. After some experimentation with Ollama and testing out local LLMs, I felt the spark return. When this blog was originally written, August 2025, the novelty of chatGPT had worn off. What most people don’t know about LLMs is that the chatGPT experience of mid 2023 can now be had on your desktop or laptop computer! Why is this important? Its important because as LLMs get better and better, running local language models will become more and more viable. In addition, it increases privacy for those who use and find value in LLMs. Its my strong opinion that a niche has opened in the AI space for those who can understand and find use cases for local LLMs.  My unique contribution to this technology shift is to show that with modest hardware, individuals can still access a GPT4 level experience as it was had circa mid 2023. Additionally, I’ll show what I observed in my home lab with various size...
Post a Comment
Read more

Nvidia's Shocking Rise Exposes the AI Truth We All Missed

Image
  Today, while listening to a business podcast on Nvidia and reflecting on its recent Q4 2023 earnings beat, an intriguing thought struck me. The analyst admitted he was wrong about Nvidia, sparking my realization about the broader perception of AI. Here's my take: Nvidia's remarkable economic growth from October 2022 to Q4 2023 isn't just a financial success story; it's a mirror reflecting our collective underestimation of AI's capabilities and advancements. This gap between perception and reality, as it narrows, is not only reshaping our understanding but also redirecting financial resources towards AI's growth, marking a pivotal moment in technology awareness. The first thing I want to address is, why am I even talking about this? Historically I tell people I’m a network engineer, but in recent times I’ve considered that I’m more of an IT infrastructure engineer. I work with VMware infrastructure, networking infrastructure, and automation with Python due...
Post a Comment
Read more

Deploying NSX Edge - Architecture & UI Together

Image
  In this blog post I'm going to discuss the NSX edge. I'll keep the explanation restricted to edges of virtual machine form factor. However, bare metal edges are also possible. The use-case for bare metal edges are high packet throughput scenarios, such as at a telco / ISP.  Architecturally, edges are the bridge between the physical network and NSX overlay network. Edges are a resource on which virtual routers and network services can be deployed. By services, I'm referring to things such as DHCP, NAT, stateful firewall, or most commonly, logical routing and switching and more.  To prepare your infrastructure for edge deployment, consider the following: Is our NSX edge cluster of a collapsed design (i.e. shared with compute cluster) or broken out into its own cluster as recommended by the NSX design guide? What is the management network? (needed: subnet, gateway, vlan, and vCenter portgroup, mgmt ip and FQDN) What network is connecting the TOR to the edge? (needed: ...
Post a Comment
Read more

Listing the Entire ESXi CLI Command Name Space

Image
ESXi command "esxcli esxcli command list" is well documented on may blogs across the web. This blogpost is simply for my personal use. In this post I've listed the namespace of command "esxcli esxcli command list" 7.0 Update 2. By listing the output here, I can review the ESXi command name space without needing to ssh to an ESXi command line.  How do you use this list? First find a command that you think will be useful. For me, the following command was of use: hardware.ipmi.bmc                                   get           Get IPMI Baseboard Management Controller (BMC) properties. Namespace                                           Command       Description --------------------------------------------------  ------------  -...
Post a Comment
Read more