Running 30B Model in Chrome Hits 32 tok/s on Mac Studio, Showcasing Local AI Power
MaziyarPanahi · x · 2026-08-12
A developer achieved 32 tokens/s running the 30B dense model Muse Glimmer entirely inside the Chrome browser on a Mac Studio.
The local setup successfully powered a clinical AI pipeline featuring PII detection, clinical NER, and relation extraction. This mind-blowing performance highlights the massive strides made in local AI inference technology.
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