Import IQ3_M quantization (3.66 bpw, 20 GB)
Browse files
mixtral-8x7b-instruct-v0.1.IQ3_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cbeffae4f9321678af2f2c89470a2f92a8f9c1ce4fbc1df59a49b9443c9c251
|
| 3 |
+
size 21427062656
|