Tag

ollama

2 essays tagged ollama.

Benchmark · 7 min

What local models actually cost you, measured on two consumer GPUs

Six open models from 0.5B to 7.6B, measured for real on an RTX 3070 and a GTX 1660 SUPER — throughput, memory, cold starts, and which ones actually get the arithmetic right. Guide · 8 min

Run AI on your own box: a practical map of local models

What actually happens when you run AI on your own hardware — what you need, what it costs, where it wins, and where the cloud still wins. No hype either way.