LFM2.5 24B (2.45B active) A2.5B
on AMD Radeon Pro W7900 · llama.cpp · 128,000 ctx
Use cases
agentictool-use
Summary
User reports LFM2.5-24B-A2B at ~95 t/s sustained on an AMD Radeon Pro W7900.
Setup is llama.cpp with ROCm, Q8 quant, full 128k context, taking 30GB VRAM.
User swapped it in for Ornith 1.5-35B in Pi Agent workflows and says it holds up well for mechanical and long-running recursive tasks; insight testing in council mode is pending.