Website profile

Liquid Ai

Liquid AI: Build efficient general-purpose AI at every scale. Liquid AI Our ultra-efficient multimodal models are turning the promise of an AI-powered world into reality. Optimized for CPUs, GPUs, and NPUs, they enable privacy-, low-latency, and security-critical applications everywhere, not just the cloud. Liquid AI i

  • 2articles · 30d
  • 3+ week agolatest article
  • Aug 18, 2026earliest in window
  • 100%with images
  • 385avg words
articles per day
Categories
  • Computers & Electronics 2
  • Science & Technology 2
  • Software Dev. 2
Bylines

Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

Liquid AI
liquid.ai > blog > lfm2.5-dspark

LFM2.5-DSpark: Up to 3.2x Faster Inference from H100 to MacBook — Blog

3+ week, 3+ day ago   (974+ words) Today, we release DSpark [1] draft model checkpoints for three models from our LFM2.5 family: LFM2.5-1.2B-Instruct, the recently released LFM2.5-2.6B, and LFM2.5-8B-A1B. These add a speculative decoding path that trades a minimal memory increase for a large decoding speedup without changing output quality. The…...