Upgrading Ollama Made Nothing Faster — But It Broke One Model
Ollama 0.32.5 was out, my workstation was still on 0.31.2, and I had just finished benchmarking 26 models on it. So I had a rare opportunity:…
Blog
Infrastructure, AI, tools, and the decisions behind them.
Ollama 0.32.5 was out, my workstation was still on 0.31.2, and I had just finished benchmarking 26 models on it. So I had a rare opportunity:…
I have an RTX 3090 sitting in a Windows workstation that is about to be torn down and rebuilt as a Proxmox AI host. Before that…
Two hosts that share a graphics card and almost nothing else, scoring that only counts what a script can verify, and the rules every number in…
The opening piece of a series in which I test what local language models actually do on hardware you can buy. This first part has no…
Venice.ai runs open-source models with zero-knowledge privacy. No prompt logging, no training on your data. The VVV token staking model gives you permanent AI access without…
How I use Tailscale to connect my homelab, data center servers, and everything in between into one encrypted mesh network. ACLs, MagicDNS, subnet routing, and why…
The hosting panel as a product category is about to be disrupted. Not by a better panel, but by AI agents that observe, reason, and act…
A compact Intel NUC running Proxmox, Ollama, and ComfyUI, connected to every server through Tailscale mesh. No cloud GPU bills, no vendor lock-in, unlimited inference for…