Some different quantizations.

#8
by ZeroWw - opened

https://huggingface.co/ZeroWw/MixTAO-7Bx2-MoE-v8.1-GGUF

My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k.

Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.

Sign up or log in to comment