Running 30B LLM in Chrome at 32 tok/s: Local AI Takes a Massive Leap
MaziyarPanahi · x · 2026-08-12
A developer tested loading a quantized 30B dense model entirely within the Chrome browser on a Mac Studio, achieving an impressive 32 tokens/second. The model successfully ran a complex clinical AI pipeline—including PII detection and clinical NER—locally, demonstrating a massive leap in local AI inference capabilities.
Related event: Meta's Open-Source Muse Glimmer 30B Impresses in On-Device Agent Tests(14 posts)→
More from Infra
- Zero's next-gen IVM engine runs in a single DO, live-querying a 100GiB R2 database — threepointone · 2026-10-16
- Meme: driving to the chip factory in 2028 captures AI's compute anxiety — beffjezos · 2026-10-16
- One volunteer maintains the time zone file behind 4 billion phones — danbri · 2026-10-16
- DeepSeek V4.1 Flash on 4x DGX Spark: weights alone are 511GB, the 494 tok/s claim doesn't fit — Aroochacha · 2026-10-16
- Open-sourced Intel GPU Vulkan inference upgrades: 2x ingestion, 60%+ faster inference — Fun-Aardvark-1143 · 2026-10-16
- ELSFP pain points: >3dB insertion loss, costly PMF, harsh packaging requirements — jwt0625 · 2026-10-16