Get the latest tech news

Mercury 3: Diffusion at scale


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.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of LLM

LLM

Photo of Diffusion

Diffusion

Photo of Mercury

Mercury

Related news:

News photo

Harness Engineering 101: The LLM is the brain, the harness is the body

News photo

Show HN: Strot – Compile an LLM's intent once, run decisions locally forever

News photo

Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware