Gabriel Cosi

Software Engineer

Systems Operational

Running LLMs at home

Building an on-demand inference box.

LLM Usage

Tokens (7d)4,053,065 tokens

Top Model (7d)qwen3.6-35b-a3b

Cluster Metrics

CPU Load31.9%

Memory42.1%

Active Pods196

Uptime33d

SLA (7d)99.97%

Global P99 (7d)157 ms