Your Data. Your Hardware. Your AI.

Practical guides for running AI locally—from someone who figured it out on a budget,
not a Silicon Valley lab.

Latest

GTX 1650 vs RTX 3060 on a 35B MoE: What the Card Buys

A $60-class GTX 1650 4 GB runs Qwen3.6-35B-A3B at 20 tok/s on 32 GB of RAM. The RTX 3060 in the same slot does 28 at the same setting and 39 tuned. Measured.

Sep 11, 2026

A 177B Model on a 3060: The 32 GB Number Nobody Measured

Qwen3.8-Flash-Next on an RTX 3090 and a 3060. Stock, the 3090 matches the video's 3060. One flag buys 34 to 40 percent. A real 32 GB box: 8.7 tok/s, not 22.

Sep 8, 2026

Nvidia PAIR Bought Me 7 Percent. My Own Router Cost Me Half.

Nvidia's new home-network AI router split 20 requests across an RTX 3090 and a 3060 for 1.07x over the 3090, then dropped half a 27B queue. Mine: 0.52x.

Sep 4, 2026

LoRA Skill Compilation Is a Double-Headed Coin Flip

Ten LoRA seeds on identical data spread 3.62 points, against 4.65 for prompt compilation. Not one beat the no-adapter base. Measured on an RTX 3090.

Sep 3, 2026

Skills in the Weights: The LoRA Answer to the Prompt Tax

Compiling a skill into a prompt costs 1,383.9 tokens per call, forever. Putting it in a LoRA costs 7.55 GB and a training run. Only one has been measured.

Aug 31, 2026

I Got the AI Result I Wanted. Then I Ran It Nine More Times

A frontier model read my logs and wrote a skill that beat my local 27B baseline by 10.6 points. Nine more compilation runs showed the number was fake.

Aug 30, 2026