AesSedai/DeepSeek-R1-0528-GGUF

This is a custom quant of DeepSeek's R1 0528 model that has the following:

• Q8_0 for the default quantization type (attention, shared experts, etc.)
• Q4_K for the FFN_UP and FFN_GATE tensors
• Q5_K for the FFN_DOWN tensors

The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization.

This model was produced using Unsloths's imatrix.