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.

Updated on: Mon Jul 08, 01:10:10

GGUF

Model size

10.7B params

Architecture

llama

Unable to determine this model's library. Check the docs .