If You Publish Benchmarks, Keep the Artifacts
In July I published an article about determinism in local models. It contains this sentence: “All 198 outputs are available in full, so that you can…
What abliteration costs — and what it doesn’t
An abliterated model scored exactly zero out of 45 on the logic puzzle. "Abliteration destroys reasoning" would have made a good headline. It just was not…
Same Prompt, Two Machines: 90 of 99 Outputs Were Byte-Identical
Eleven local models, three real tasks, two RTX 3090 hosts, 198 requests, zero errors. 90 of 99 outputs came back byte-identical across machines — and the…
The model that couldn’t stop
One model sits at the bottom of the table with 35 percent. The number was measured honestly — and is still wrong, in both directions at…
Reserving 128k Context Costs Nothing. Filling It Costs Two Thirds.
Two RTX 3090s, eleven models with identical digests, 528 requests and no errors. Reserving a 128k KV cache is nearly free; filling it costs 10 to…
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:…
I Benchmarked 26 Local LLMs on One RTX 3090 — Here Is What Actually Held Up
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…
How I Measure: The Ground Rules Before Any Numbers
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…
Starting a Series on Local Models — First, the Vocabulary
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…
My AI Homelab Setup: RTX 3090, Proxmox, Ollama, and Tailscale
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…