Custom GGUF quants of Meta’s [Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), where the Output Tensors are quantized to Q8_0 or kept at F32, and the Embeddings are kept at F32. Enjoy! 🧠🔥🚀

Notes: Great SMOL LLM for on-device inference for mobile devices. 😋