mradermacher/granite-speech-4.1-2b-i1-GGUF
Quantization (fewer layers) vs ibm-granite/granite-speech-4.1-2b. mradermacher/granite-speech-4.1-2b-i1-GGUF matches part of ibm-granite/granite-speech-4.1-2b (363 of its 954 tensors; the rest of ibm-granite/granite-speech-4.1-2b has no counterpart). On the shared part: mradermacher/granite-speech-4.1-2b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 81 tensors match exactly and 282 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1