Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ Full offload possible on 48GB VRAM with a huge context size :
|
|
16 |
Full offload possible on 36GB VRAM with a variable context size (up to 7168 with Q3_K_M, for example)
|
17 |
|
18 |
Q3_K_M, Q3_K_S, Q3_K_XS,
|
19 |
-
IQ3_XXS SOTA (which is equivalent to a Q3_K_S with more context! (filename is partly wrong,
|
20 |
Lower quality : Q2_K, Q2_K_S
|
21 |
|
22 |
Full offload possible on 24GB VRAM with a decent context size.
|
|
|
16 |
Full offload possible on 36GB VRAM with a variable context size (up to 7168 with Q3_K_M, for example)
|
17 |
|
18 |
Q3_K_M, Q3_K_S, Q3_K_XS,
|
19 |
+
IQ3_XXS SOTA (which is equivalent to a Q3_K_S with more context! (filename is partly wrong, ch2500 is the real values))
|
20 |
Lower quality : Q2_K, Q2_K_S
|
21 |
|
22 |
Full offload possible on 24GB VRAM with a decent context size.
|