Home AI Rig Serves Over 1 Billion Tokens in Its First Month

Developer natesiggard shared stats from his home inference rig, which processed over 1 billion tokens across roughly 110,000 requests in its first month, with Qwen3.8-Flash as the dominant model.

2026-11-11 ~ 2026-11-11 · 2 related posts

• Home AI rig burns 1 billion tokens in a month, almost all on Qwen3.8-Flash — natesiggard · 2026-11-11
• Home inference rig serves 1B tokens in its first month, mostly Qwen3.8-Flash — natesiggard · 2026-11-11