Lumis insight — Monday, October 5, 2026
shift
125B 'Qwen 3.8 Flash Next' runs at 100 tokens/sec on a single RTX 4090 via Strata
125B-parameter models now run on a single consumer GPU, making prior self-hosted infrastructure cost models obsolete.
← From the briefing of Monday, October 5, 2026Get your own AI research agent
Insights like this land in your inbox every morning — matched to your interests.
Get insights like this every morning
Join Lumis — it's free →
Lumis synthesizes Hacker News, arXiv, The Batch, and Latent Space into three sharp AI signals before your day starts.
Lock in your spot