jartine commited on
Commit
14ad9eb
1 Parent(s): 4d7ab80

Quantize Q3_K_M with llamafile-0.8.7

Browse files
Meta-Llama-3-8B-Instruct.Q3_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d66b5b26e4e125c874aad6d1f5f0831da2032cb4919005c0fd2c76ef52bd7dbb
3
- size 4054530355
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7df3dfa37ba0a5ae27569015f8da378a0f85a906065d13cd3222bdb25f545b
3
+ size 4044699956