mradermacher/granite-speech-3.3-2b-i1-GGUF
Quantization (fewer layers) vs ibm-granite/granite-speech-3.3-2b. mradermacher/granite-speech-3.3-2b-i1-GGUF matches part of ibm-granite/granite-speech-3.3-2b (362 of its 953 tensors; the rest of ibm-granite/granite-speech-3.3-2b has no counterpart). On the shared part: mradermacher/granite-speech-3.3-2b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 81 tensors match exactly and 281 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160