ghostai1 commited on
Commit
c0569a8
·
verified ·
1 Parent(s): 3cec767

Upload ghostai-horror-7b.Q3_K_S.gguf

Browse files

### Q3_K_S (GHOSTAI Horror 7B) — Small / Speed-Oriented
Smaller and faster than Q3_K_M with a bit more quality loss.
Best for: tight RAM budgets where you still want usable chat quality.

Files changed (2) hide show
  1. .gitattributes +1 -0
  2. ghostai-horror-7b.Q3_K_S.gguf +3 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ghostai-horror-7b.TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
37
  ghostai-horror-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  ghostai-horror-7b.TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
37
  ghostai-horror-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ ghostai-horror-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ghostai-horror-7b.Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f30b00d922466998a6bab468d8ac825011ec202890eeb3fab491093d7824058
3
+ size 3168525824