Sina Semnani on X: “Our latest VLM now decodes up to 3x faster:”

A fast, private reader for public X posts. No account, no tracking, no pop-ups.

PeekX is an independent tool and is not affiliated with, endorsed by or sponsored by X Corp. “X” and “Twitter” are trademarks of their respective owners. We only show posts that their authors made public and never access private or protected accounts. Downloaded media belongs to its creators — please respect their rights.

Sina Semnani on X: “Our latest VLM now decodes up to 3x faster:” | PeekX

Username or post link

Home / @sina_semnani / Post

Sina Semnani

@sina_semnani

Our latest VLM now decodes up to 3x faster:

Liquid AI@liquidai · Sep 24

Today, we release an experimental DSpark draft model for LFM2.5-VL-3B, bringing speculative decoding to our vision-language models.

A lightweight drafter proposes multiple tokens ahead, and the target model verifies them together in a single pass. This accelerates generation

GIF

Open quoted post →

Sep 24, 2026, 8:04 PM UTC

0 24

Download media

Every quality X serves, straight from X's media CDN. No watermark, no wait.

From the quoted post by @liquidai

GIF (MP4)BEST

GIF as MP4 · 1920×1080

Save & share

Turn this post into a clean image, or copy it as text or Markdown.

Open on X