Description

GGUF quantized versions of StepFun's flagship 604B-class sparse Mixture of Experts model, optimized for local inference. The repository includes various quantization levels such as 1-bit IQ1_S and 2-bit Q2_K, along with the necessary sidecar files for the perception encoder and MTP layers required for llama.cpp execution.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.