Inkling 2 Mini hits 210 tok/s locally on M5 Ultra, builds app 1.8x faster and 11x cheaper than Claude

pcuenq · x · 2026-11-22

ExoLabs partnered with Thinking Machines to run Inkling 2 Mini fast on local Macs:

In a real test it built a native weather app 1.8x faster than Claude Sonnet 5.5 via API, at 11x lower cost.

The key is the looping architecture: cycling through model layers adds inference-time compute (and intelligence) without growing the model, which suits memory-constrained devices. An HF staffer called it a sign that local, open-source AI is how the underdog wins.

Related event: Inkling-2 Mini Hits 210 tok/s Locally on Apple Silicon, 11x Cheaper than Sonnet(4 posts)→

Original post →

More from Infra

Infra channel →