cstr/harrier-270m-GGUF
Quantization vs microsoft/harrier-oss-v1-270m. cstr/harrier-270m-GGUF is a GGUF quantization (Q8_0) of the same weights: 109 tensors match exactly and 127 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/109, MLP 0/54, Attention 0/72