tensorblock/tiny-mixtral-GGUF
Quantization vs TitanML/tiny-mixtral. tensorblock/tiny-mixtral-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 7 tensors match exactly and 10 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/2, Norms 0/5, Attention 0/8