mradermacher/AI21-Jamba2-3B-i1-GGUF
Quantization vs ai21labs/AI21-Jamba2-3B. mradermacher/AI21-Jamba2-3B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 57 tensors match exactly and 94 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/8