version = 1

; (Optional) This section provides global settings shared across all presets.
; If the same key is defined in a specific preset, it will override the value in this global section.
[*]
c = 8192  # works good
; c = 16400  # works less well
# c = 2048  # works terrible


; When you ask for too many layers, llama.cpp fails at load time with a CUDA out of memory error. It will not silently fall back. It stops.

; The fix is to drop ngl by a few and reload. Step down until it loads. If you are right at the edge, shave 2 or 3 layers and try again.

; Watch your VRAM with nvidia-smi while the model loads. You want a buffer left over, not a card pinned at 100 percent. Other apps, your desktop, and the KV cache all want a slice.

; 8 was fine, 16 was fine
n-gpu-layers = 16