Skip to content

llama quantize

Latest

Choose a tag to compare

@shira-qwq shira-qwq released this 01 Jul 14:00
· 7 commits to main since this release

Compiled from llama.cpp
Patched with ComfyUI-GGUF/tools/lcpp.patch
Built for Windows
CUDA build/version: CUDA 13.1
Target tool: llama-quantize.exe
Purpose: quantizing Flux/RUM image-model GGUF
Not a general-purpose official llama.cpp release