ModelLFM3 1.7B
LFM3-1.7B
A 1.7B-parameter open-weight model in Liquid AI's LFM3 series. It uses a tri-hybrid mixed backbone architecture and supports a 256K context window. At 4-bit quantization it occupies approximately 1GB, targeting memory-constrained on-device scenarios.
Timeline (last 90 days)
Oct 27
LFM3-1.7B adopts a tri-hybrid backbone structure, supports a 256K context window, and is about 1GB in size under 4-bit quantization.
Unverified50%