Layer-wise quantization Q8_0

Dolphin3.0-R1-Mistral-24B-Q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5df87b6b16ef0bf713efbbcf3d842890cc4812b26c2da40c6bdf6fb3865909f
-size 25054803936
+oid sha256:2442f6567c043680422ed3dae7a7076bfd424db7faba4daf80646d66f475dd6e
+size 22976159360