---
title: "Discussion on \"Mercury 2: Inception's Diffusion LLM at 1,000 Tokens/s\" | Hashnode"
description: "Discussion on \"Mercury 2: Inception's Diffusion LLM at 1,000 Tokens/s\". Most language models work like a very fast typist: one token at a time, left to right, no going back. Mercury 2 from Inception Labs works more like an editor: it starts with a rough draft and refines the whole thing in parallel until it converges on ..."
url: "https://hashnode.com/posts/mercury-2-inception-diffusion-llm-production-guide-2026/69f7050928a517bb23c54125"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Mercury 2: Inception's Diffusion LLM at 1,000 Tokens/s](https://effloow.hashnode.dev/mercury-2-inception-diffusion-llm-production-guide-2026?utm_source=hashnode&utm_medium=feed)

Most language models work like a very fast typist: one token at a time, left to right, no going back. Mercury 2 from Inception Labs works more like an editor: it starts with a rough draft and refines the whole thing in parallel until it converges on ...

May 3 · 10 min read · effloow.hashnode.dev  
Read the article

-   [#inception-labs](https://hashnode.com/tag/inception-labs)
-   [#diffusion-llm](https://hashnode.com/tag/diffusion-llm)
-   [#llm-speed](https://hashnode.com/tag/llm-speed)
-   [#agentic-ai](https://hashnode.com/tag/agentic-ai)
-   [#mercury-2](https://hashnode.com/tag/mercury-2)

## Written by

[Jangwook Kim](https://hashnode.com/@effloow)

@effloow · Tokyo, Japan

  
[View profile](https://hashnode.com/@effloow)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
