Home AI rig burns 1 billion tokens in a month, almost all on Qwen3.8-Flash
natesiggard · x · 2026-11-11
A developer shows the inference dashboard on his home rig (ROIE): 1,001,081,028 tokens and 110K requests since Oct 11 — one month of heavy local use, nearly all on Qwen3.8-Flash-Next-NV (958M read / 42.8M written), with a copy kept on a Raspberry Pi. Speech and image models report no tokens. A real-world sample of sustained at-home AI usage.
Related event: Home AI Rig Serves Over 1 Billion Tokens in Its First Month(2 posts)→
More from Infra
- NEAR AI discloses SGLang vulnerability exploit, touts TEE as the fix — AccBalanced · 2026-11-11
- Polymarket puts 17% odds on orbital AI data centers by 2027 as Google launches Suncatcher — Polymarket · 2026-11-11
- Developer drops $10B Michigan data center after residents reject $54M tax promise — Polymarket · 2026-11-11
- Rumor: DeepSeek to pretrain ~2T-param V5 on Huawei Ascend 950, release may slip to 2027 — teortaxesTex · 2026-11-11
- WSJ: Masayoshi Son Over-Reserved a Big Chunk of the Gas Turbine Market in AI Frenzy — mattwbaker · 2026-11-11
- FT: Commerce Dept stalls Megaspeed export blacklist despite 4 agencies pushing over Nvidia chip smuggling — rohanpaul_ai · 2026-11-11