Inception launches Mercury 2.5: diffusion LLM with 40% intelligence jump at 1,100 tokens/sec
volokuleshov · x · 2026-09-10
Inception AI announced Mercury 2.5, calling it the most capable diffusion LLM on the market: a 40% intelligence jump over Mercury 2, running at over 1,100 tokens/sec on widely available NVIDIA GPUs.
The team positions it for the agent stack: most agent calls aren't writing the final answer — they're rewrites, reranks, compactions, and tool searches, where latency and cost compound. Mercury 2.5 aims to own that entire layer with speed and low cost.
The launch post also previews a dLLM optimized for voice agents and a dLLM used as a router to route requests to the best models.
More from coding & agent
- Precompute golden answers and match at runtime: an LLM pattern from AustinLangChain — colinmcnamara · 2026-10-27
- Dev argues there's still alpha in working with your coding agent interactively — alex_frantic · 2026-10-27
- Researchers launch AMA on patterns for safer AI agents used by citizen developers — Loose_Rip359 · 2026-10-27
- Gradio Adds In-Chat Human-in-the-Loop So ML Intern Pauses Before Training — Gradio · 2026-10-27
- Building Halo Infinite Forge maps with local LLMs, DCjson and Blender MCP — swagonflyyyy · 2026-10-27
- Ex-Unity dev Lucas Meijer says OpenClaw looks cleaned up and worth another run — lucasmeijer · 2026-10-27