Gabriel Cosi

Software Engineer

Systems Operational

Running LLMs at home

Building an on-demand inference box.

LLM Usage

Tokens (7d)17,003,843 tokens

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

Cluster Metrics

CPU Load37.9%

Memory43.4%

Active Pods197

Uptime38d

SLA (7d)99.8%

Global P99 (7d)509 ms