Topic: inference speed

1 article

Explore our coverage of inference speed — 1 curated articles, summaries, and related resources from the Inblix archive.

Nvidia's Nemotron 3.5 Lightning hits 670 tokens/sec with just 3.6B active parameters

The Decoder · Aug 11, 2026 · 3 min read

Nvidia just dropped Nemotron 3.5 Lightning, and the numbers tell a very specific story. This is a 31.6-billion-paramete...