win10/Llama-3.2-3B-Instruct-24-9-29

Same weights, converted vs unsloth/Llama-3.2-3B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

2 derivatives checked

• mradermacher/Llama-3.2-3B-Instruct-24-9-29-i1-GGUF: Quantization
• mradermacher/Llama-3.2-3B-Instruct-24-9-29-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse