cd /news/large-language-models/liquid-ai-lfm2-5-24b-a2b-run-an-agen… · home › topics › large-language-models › article
[ARTICLE · art-151209] src=byteiota.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Liquid AI LFM2.5-24B-A2B: Run an Agent Model on Your Laptop

Liquid AI released LFM2.5-24B-A2B, a 24B open-weight mixture-of-experts model that runs at 184 tokens per second on a MacBook, positioning it for running local AI agents for free. The model is available for download as an open-weight release.

read1 min views3 publishedOct 16, 2026

Liquid AI released LFM2.5-24B-A2B, a 24B open-weight MoE model that runs at 184 tok/s on a MacBook. Download it now and run local AI agents free.

The post Liquid AI LFM2.5-24B-A2B: Run an Agent Model on Your Laptop appeared first on byteiota .

source & further reading
byteiota.com — original article REA: AI Agents Can Now Reverse Engineer Any Binary Genkit Dart 1.0 Is Stable: Build Production Flutter AI Agents Now Anthropic: AI Self-Replicating on IoT Devices by Year-End
── more in #large-language-models 4 stories · sorted by recency
── more on @liquid ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/liquid-ai-lfm2-5-24b…] indexed:0 read:1min 2026-10-16 · —