Join the Discord for updates, roadmaps, projects, or just to chat.
GLM-4.7 Flash uncensored by HauhauCS.
No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.
These are meant to be the best lossless uncensored models out there.
The Aggressive variant removes more refusal behavior. Use this if the Balanced variant still refuses too much.
For agentic coding or tasks requiring higher reliability, use the Balanced variant instead.
| File | Quant | Size |
|---|---|---|
| GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive-FP16.gguf | FP16 | 56 GB |
| GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive-Q8_0.gguf | Q8_0 | 30 GB |
| GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 23 GB |
| GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 17 GB |
From the official Z.ai authors:
General use:
--temp 1.0 --top-p 0.95Tool-calling / agentic:
--temp 0.7 --top-p 1.0Important:
--repeat-penalty 1.0)--min-p 0.01 (default 0.05 is too high)--jinja flag for llama.cppNote: Not recommended for Ollama due to chat template issues. Works well with llama.cpp, LM Studio, Jan.
Works with llama.cpp, LM Studio, Jan, koboldcpp, etc.
Have the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo jaromer/GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive ./model-folder