oxide-lab/whisper-medium-GGUF
Quantization vs openai/whisper-medium. oxide-lab/whisper-medium-GGUF is a GGUF quantization (Q8_0) of the same weights: 2 tensors match exactly and 945 within quantization error.
Tensors changed: Embeddings 0/3, Norms 0/244, Attention 0/504, MLP 0/192, other 0/4