Inception "Mercury 3", 1000 tok/s diffusion LLM
Article, Comments
www.inceptionlabs.ai
Diffusion at Scale: Introducing Mercury 3 – Inception
Mercury 3 is the most capable diffusion LLM released to date. It outperforms GPT-6 Luna and Claude Haiku 5.5 while running 4–8x faster at 1,000+ tokens per second.
11
4
2
1October 19, 2026 2.6K 45
