Blue Beck’s Llama Aligned DeepSeek R1 Distil models are fine tuned versions of Deep Seek AI's 8B and 70B R1-Distil models that culturally align with Meta’s Llama 3 series in order to be more suitable for public facing deployment in western countries, while retaining the reasoning capabilities the R1 based models are famous for.

If you are looking to run the models on an Apple Silicon Mac click here.

If you are looking to run the models using your computer's GPU from AMD, NVIDIA or Intel with just gaming drivers click here.

If you are looking to run the models using a single NVIDIA GPU and Cuda drivers (for best performance) click here.

If you are looking to run the models using multiple NVIDIA GPUs click here.

If you are looking to run the models using just your computer's CPU click here.