CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF
Quantization vs CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B. CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 145 tensors match exactly and 130 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/160, Attention 0/32