---
title: "LFM 2.5-2.6B by @liquidai just launched and it punches above its weight!"
date: 2026-08-04
canonical: https://solmaz.io/x/2084668050415272218/
x_url: https://x.com/onusoz/status/2084668050415272218
license: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
---

LFM 2.5-2.6B by @liquidai just launched and it punches above its weight!

It can run 32 sessions (and more) in parallel with hundreds of output tokens per second aggregate throughput, on the DGX Spark!

And this is just the base vLLM config on release date, I expect it to be optimized a lot more!

*Quotes a post by @liquidai (https://x.com/liquidai/status/2084640701669613906); its text is omitted here because it is not covered by this site's license.*