Hugging Face's logo

Nexesenex
/
llama-3-70B-Instruct-abliterated-CQ-GGUF

GGUF
Model card Files Community
Nexesenex commited on
Commit
60a5567
•
1 Parent(s): 24c3a9c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -1,4 +1,6 @@
1
  Custom GGUF quant for :
2
  failspy/llama-3-70B-Instruct-abliterated-GGUF
3
 
4
- Optimal (8k ctx) for 36GB VRAM with an IGP displaying the OS.
 
 
 
1
  Custom GGUF quant for :
2
  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.