FINAL-Bench/POCKET-EN-GGUF
Quantization vs FINAL-Bench/Darwin-36B-Opus. FINAL-Bench/POCKET-EN-GGUF is a GGUF quantization (IQ2_XXS/Q4_K) of the same weights: 101 tensors match exactly and 162 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/101, MLP 0/120, Attention 0/40