Q4_0_4_4 gguf
#3
by
Yuma42
- opened
This model is the top llama model of its size since a while in the leaderboard. I also made good experience with it. Would it be possible to get a Q4_0_4_4 gguf for it? Maybe @bartowski can even make imatrix Q4_0_4_4
Maybe the same request can also be made for Joseph717171/Llama-3.1-8B-InitializedEmbeddings_with_Hermes-3 but I didn't test that one.
Sure I'll throw it up :)