ik_llama.cpp/examples/quantize-stats
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
..
CMakeLists.txt Trellis quants with CPU inference (#441) 2025-05-23 09:17:52 +03:00
quantize-stats.cpp Experiments for 2.6875 bpw quants 2025-07-13 20:15:19 +03:00