theprint-MoE-8x3-0126-GGUF

An 18B parameter Mixture of Experts model combining 8 specialized 3B experts, with 2 experts activated per token by default (configurable up to 4 at inference).

Architecture

• Base model: theprint/GeneralChat-Llama3.2-3B (provides shared attention layers)
• Total parameters: ~18B
• Active parameters: ~5B (2 experts) or ~9B (4 experts)
• Gate mode: Hidden (prompt-based router initialization)

Full Model

For more information about this model, including access to the safetensor files, please see theprint/theprint-moe-8x3-0126.