nisten
/

meta-405b-instruct-cpu-optimized-gguf

Model card Files Files and versions

nisten commited on Jul 24, 2024

Commit

347517f

·

verified ·

1 Parent(s): c4c11e4

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -9,9 +9,9 @@ This repository contains CPU-optimized GGUF quantizations of the Meta-Llama-3.1-
 ## Available Quantizations
-1. Q4_0_48 (CPU Optimized): ~264 GB
-2. BF16: ~855 GB
-3. Q8_0: ~435 GB
 4. more coming...
 ## Use Aria2 for parallelized downloads, links will download 9x faster

 ## Available Quantizations
+1. Q4_0_48 (CPU Optimized): ~246 GB
+2. BF16: ~820 GB
+3. Q8_0: ~410 GB
 4. more coming...
 ## Use Aria2 for parallelized downloads, links will download 9x faster