LFM2.5-8B-A1B-GGUF
Overview
Liquid's LFM2.5 uses a hybrid A1B architecture for high throughput at low cost. An efficient everyday model that runs comfortably in 16 GB.
Recommended hardware
≈ 16 GB VRAM to run this 8B model at the Q8_0 quantization.
Fits 16 GB+ consumer GPUs (e.g. RTX 4060 Ti 16GB, RTX 4080)