jsbeaudry/Oswald-ASR-0.6-V1-GGUF
Quantization (fewer layers) vs jsbeaudry/Oswald-ASR-0.6-V1. jsbeaudry/Oswald-ASR-0.6-V1-GGUF matches part of jsbeaudry/Oswald-ASR-0.6-V1 (310 of its 611 tensors; the rest of jsbeaudry/Oswald-ASR-0.6-V1 has no counterpart). On the shared part: jsbeaudry/Oswald-ASR-0.6-V1-GGUF is a GGUF quantization (Q8_0) of the same weights: 113 tensors match exactly and 197 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112