You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Right now it seems GPT4All Vulkan backend only supports Q4_0 and Q4_1 quantization.
Are there plans to support other common quantizations, like the very popular Q4_K_M?
The text was updated successfully, but these errors were encountered:
Feature Request
Right now it seems GPT4All Vulkan backend only supports Q4_0 and Q4_1 quantization.
Are there plans to support other common quantizations, like the very popular Q4_K_M?
The text was updated successfully, but these errors were encountered: