Description

Ling-3.0-flash is a 124B parameter Mixture of Experts (MoE) model built on a native hybrid linear architecture (KDA+MLA). It features a highly efficient 5.1B active parameter count per token, allowing for fast decoding on hardware like the DGX Spark when running quantized GGUF versions.

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