mradermacher/StepFun-Prover-Preview-32B-GGUF
Quantization vs stepfun-ai/StepFun-Prover-Preview-32B. mradermacher/StepFun-Prover-Preview-32B-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448