dranger003/starcoder2-15b-instruct-iMat.GGUF
Quantization vs TechxGenus/starcoder2-15b-instruct. dranger003/starcoder2-15b-instruct-iMat.GGUF is a GGUF quantization (Q8_0) of the same weights: 402 tensors match exactly and 242 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/162, MLP 0/160, Attention 0/320, lm_head 0/1