legraphista/Reflection-Llama-3.1-70B-IMat-GGUF

Same weights, converted vs mattshumer/Reflection-Llama-3.1-70B. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/320, Norms 0/161, lm_head 0/1

On the Hub · Downloads on Model Pulse