Inception "Mercury 3", 1000 tok/s diffusion LLM
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.
Summary
Mercury 3 is a new diffusion language model that surpasses competitors like GPT-6 Luna and Claude Haiku 5.5 in both performance and speed, achieving over 1,000 tokens per second. Its impressive capabilities make it a noteworthy development in the field of AI language processing.
Comments (91 of ) ⌛