mradermacher/Step-3.5-Flash-REAP-149B-A11B-GGUF
Quantization vs cerebras/Step-3.5-Flash-REAP-149B-A11B. mradermacher/Step-3.5-Flash-REAP-149B-A11B-GGUF is a GGUF quantization (Q8_0) of the same weights: 223 tensors match exactly and 488 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/181, MLP 0/261, Attention 0/225, other 0/42, lm_head 0/1