diffuse-cpp/LLaDA-8B-Instruct-GGUF

Quantization vs GSAI-ML/LLaDA-8B-Instruct. diffuse-cpp/LLaDA-8B-Instruct-GGUF is a GGUF quantization (Q8_0) of the same weights: 66 tensors match exactly and 225 within quantization error.

Tensors changed: Attention 0/128, Norms 0/65, Embeddings 0/1, other 0/65, MLP 0/32

On the Hub · Downloads on Model Pulse