mradermacher/AReaL-tau2-merge-sft-235B-i1-GGUF
Quantization vs inclusionAI/AReaL-tau2-merge-sft-235B. mradermacher/AReaL-tau2-merge-sft-235B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 471 tensors match exactly and 378 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/377, MLP 0/94, Attention 0/376, lm_head 0/1