mlx-community/llama-3.3-70b-instruct-fp16
Same weights, converted vs meta-llama/Llama-3.3-70B-Instruct. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1
Same weights, converted vs meta-llama/Llama-3.3-70B-Instruct. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1