4rchive
[
Home
] [
Feed
] [
Search
]
Report Content
Post Preview
Anonymous
8/6/2025, 5:11:36 AM
No.106158404
How do you understand what quantization to use? For example with llama.cpp and GLM 4.5 Air if it differs based on model or backend.
16 vram, 64 ram.
Description *
Submit Report