Files
ik_llama.cpp/examples/quantize-stats/quantize-stats.cpp
Iwan Kawrakow b7c986e4ff Experiments for 2.6875 bpw quants
At least according to rmse, this is significantly better than
q2_K, while using only 1/16 more bits per weight.
2025-07-13 20:15:19 +03:00

73 KiB