mlx-community/Llama-3.2-3B-Instruct
Same weights, converted vs meta-llama/Llama-3.2-3B-Instruct. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112
3 derivatives checked
- mlx-community/Llama-3.2-3B-Instruct-4bit: Quantization
- adeelahmad/ReasonableLlama3-3B-Jr: Full fine-tune
- bestler/Code-Summary-Llama-3.2-3B-Instruct: LoRA-style
1 other repos hold byte-for-byte identical weight files.