Skip to main content
← Back to news

Tokspur: the open source inference engine claiming 3x speed on Macs

Tools & releases
Source:GitHub
Tokspur is an open source inference engine for Apple Silicon built on Metal: claims speak of decode up to three times faster than classic engines on MacBook and Mac Studio. Numbers should be taken with a grain of salt until independent benchmarks exist.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.