mradermacher/RLVR-8B-0926-i1-GGUF
Quantization vs stepfun-ai/RLVR-8B-0926. mradermacher/RLVR-8B-0926-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144, Embeddings 0/1, lm_head 0/1