LFM2.5 24B (2.45B active) A2.5B
on M5 Max · 131,072 ctx
Use cases
agentictool-usemultilinguallong-context
Summary
User reports LFM2.5-24B-A2B at 184 tok/s on an Apple M5 Max.
Setup is GGUF weights with a 131,072-token context length.
The figure is the vendor's on-device claim; the same release is quoted at up to 21K output tok/s on a single NVIDIA B300 GPU. The model is a 24B-parameter MoE with 2.45B active parameters, 64 experts per block with top-4 routing, and 36 trillion training tokens.