Nexesenex commited on
Commit
6f99130
1 Parent(s): 098c8fb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -3,4 +3,6 @@ failspy/llama-3-70B-Instruct-abliterated-GGUF
3
 
4
  IQ4_SR is Optimal (8k ctx) for 36GB VRAM with an IGP displaying the OS.
5
 
 
 
6
  Without an IGP, the IQ4_XSR is for you.
 
3
 
4
  IQ4_SR is Optimal (8k ctx) for 36GB VRAM with an IGP displaying the OS.
5
 
6
+ IQ4_MR is optimal for the same config with MMQ and KV quants (8 bits)
7
+
8
  Without an IGP, the IQ4_XSR is for you.