LiquidAI/LFM2.5-350M
Liquid AI's smallest LFM2.5 chat model (350M) on the LFM2 hybrid conv+attention backbone — tool calling and 32K context, light enough for edge GPUs.
350M hybrid instruct model with tool calling — fits any GPU, ideal for edge / on-device serving
View on HuggingFace
View on ModelScope