wimmmm/Cerebras-Step-3.5-Flash-REAP-149B-A11B-GGUF
Same weights, converted vs cerebras/Step-3.5-Flash-REAP-149B-A11B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 43 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/181, MLP 0/261, Attention 0/225, other 0/42, lm_head 0/1