Gabriel Cosi

Software Engineer

Systems Operational

Running LLMs at home

Building an on-demand inference box.

LLM Usage

Tokens (7d)7,539,704 tokens

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

Cluster Metrics

CPU Load33.6%

Memory42%

Active Pods200

Uptime29d

SLA (7d)99.97%

Global P99 (7d)112 ms