AINewsnow

Serving LFM2.5-24B-A2B on one 48 GB GPU: the flags, the traps and what to measure

This story is from 2026-10-27. It is preserved in the archive; the latest stories are on the live feed.

Liquid AI built LFM2.5-24B-A2B for agents on your own hardware. It has 24.0B parameters in total, the learned numbers that make up the model. Only 2.45B of them work on each token, the word piece a model reads and writes. Liquid ships an official FP8 checkpoint, a copy that stores most weights in 8…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-10-27 06:20 · DEV Community — AI
    Serving LFM2.5-24B-A2B on one 48 GB GPU: the flags, the traps and what to measure

More stories

  1. Moonshot AI launches Kimi K3.1 Pro with better coding skills, reduced cyber risks — Mint AI
  2. Introducing GPT-6.1 Terra — OpenAI News
  3. Meta announces $95B offering to fund AI — Semafor Technology
  4. Anthropic's Claude bypassed a paywall to access Georgia voter data without authorization — Axios AI+
  5. CoreWeave Builds the First Global Backbone Network Purpose-Built for AI — CoreWeave Blog
  6. Microsoft offers buyouts to 60,000 employees — The Verge AI
  7. OpenAI announces three breakthroughs in computer science, math, and physics, including that the Exponential Time Hypothesis, a longstanding conjecture, is false (OpenAI) — Techmeme
  8. Anthropic’s IPO filing lays out a plan to ‘revolutionize every area of human endeavor' with AI — The Verge AI

Get the daily brief of stories like this at 6:30 every morning →