LFM2.5-24B-A2B beats Qwen3.6 at tools and loses SWE-Bench by 15 points
Liquid AI released LFM2.5-24B-A2B with open weights. We read the full benchmark table and the license: strong at tool calls, weak at coding, and not free for every company.
Liquid AI released LFM2.5-24B-A2B with open weights. We read the full benchmark table and the license: strong at tool calls, weak at coding, and not free for every company.
Stéphane Cardon, network cybersecurity engineer. Architecture, LAN and WLAN, system administration. PacketNebula holds the tools and answers he wanted for his own work.
Copyright © 2026 Stephane Cardon.
Cookies, your call
We use Google Analytics to see which pages get read. Once our AdSense application is approved, articles and guides will carry Google ads. Nothing runs until you say yes, and nothing runs on the tool pages. Details