Gabriel Cosi

Software Engineer

Systems Operational

Running LLMs at home

Building an on-demand inference box.

LLM Usage

Tokens (7d)4,060,193 tokens

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

Cluster Metrics

CPU Load31.9%

Memory42.5%

Active Pods195

Uptime33d

SLA (7d)99.97%

Global P99 (7d)115 ms