Update admin_manual/ai/app_llm2.rst

Co-authored-by: Josh <josh.t.richards@gmail.com>
Signed-off-by: Marcel Klehr <mklehr@gmx.net>
This commit is contained in:
Marcel Klehr 2024-06-24 12:39:41 +02:00 committed by GitHub
parent 5c881f087c
commit 2995d98bf3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -24,7 +24,7 @@ Requirements
* You will need a GPU with enough VRAM to hold the model you choose
* here are some examples:
* Some examples:
* for 8B parameter models, 5bit-quantized variants and lower should fit on a 8GB VRAM, but of course have slightly lower quality
* for 8B parameter models, 6bit-quantized variants and up will need 12GB VRAM