
Measuring LFM2.5-24B-A2B Throughput Against Real Agent Turn Latency
pr0h0•
A hands-on benchmark of Liquid AI's LFM2.5-24B-A2B mixture-of-experts model that tests whether its reported 184 tokens per second survives contact with real agent turn latency, including tool calls, retries, and growing context.
llm-inferencemixture-of-expertsedge-ai
