Running 30B Models Locally in Chrome at Over 30 tok/s
MaziyarPanahi · x · 2026-08-13
A developer successfully ran the Muse Glimmer 30B dense model entirely locally inside the Chrome browser. It achieved an inference speed of 31.6 tokens/second while handling tasks like clinical PII, Named Entity Recognition (NER), and relation extraction. This demonstrates the significant potential for deploying large AI models directly in browsers.
More from Infra
- Tencent squeezes 770B-parameter Hunyuan Hy4 Preview into 214 GiB at ~2.38 bits per weight — coolmum18 · 2026-10-16
- TokenSpeed MLA 2 hits NVIDIA Vera Rubin: up to 3.44x faster decode vs B200 — zhyncs42 · 2026-10-16
- US vs Chinese hyperscalers: Americans fund and schmooze, Chinese demand your BoM and cap you at 7% margin — jwt0625 · 2026-10-16
- How LiteLLM routes one OpenAI-shaped API across every model provider — Mahmoud_Zalt · 2026-10-16
- OpenAI-Broadcom custom AI chip Jalapeño named a TIME Best Invention of 2026 — itsclivetime · 2026-10-16
- Developer live-runs continual pretraining of a Luganda LLM on Colab, 41% done with loss dropping fast — weskambale · 2026-10-16