markldn/LLaDA-MoE-7B-A1B-Instruct-Q4_K_M-GGUF

Quantization vs inclusionAI/LLaDA-MoE-7B-A1B-Instruct. markldn/LLaDA-MoE-7B-A1B-Instruct-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 81 tensors match exactly and 66 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/16, Attention 0/64, lm_head 0/1

On the Hub · Downloads on Model Pulse