license: apache-2.0
library_name: gguf
tags:
- gguf
- qwen3.6
- mtp
- llama.cpp
- coding
- uncensored
- speculative-decoding
Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
This GGUF was created by grafting Qwen3.6 27B MTP tensors from 27B_MTP.gguf onto HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf using the public GGUF MTP transplant workflow.
Credit to the original HauhauCS model authors and to the public MTP conversion work this method builds on.
Optimized Agentic Run
Tool-calling on llama.cpp with CUDA 13.3+ using WebUI:
llama-server.exe ^
-m "Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-MTP-Q4_K_P.gguf" ^
--jinja ^
--spec-type draft-mtp ^
--spec-draft-n-max 1 ^
--spec-draft-ngl 100 ^
-ngl 100 ^
-np 1 ^
-fa on ^
-c 262144 ^
--context-shift ^
-ctk q4_0 ^
-ctv q4_0 ^
--host 127.0.0.1 ^
--port 8033 ^
--tools read_file,file_glob_search,grep_search,exec_shell_command,write_file,edit_file,apply_diff