mradermacher/openbuddy-zen-56b-v21.2-32k-GGUF
Quantization vs OpenBuddy/openbuddy-zero-56b-v21.2-32k. mradermacher/openbuddy-zen-56b-v21.2-32k-GGUF is a GGUF quantization (Q6_K) of the same weights: 201 tensors match exactly and 702 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/201, MLP 0/300, Attention 0/400, lm_head 0/1