Uncensored version of GPT-OSS 20B. This is the balanced variant - more conservative tuning that prioritizes keeping the model's general capabilities intact.
If you want fewer refusals and don't mind being a bit more experimental, check out the
Aggressive variant.
MXFP4 GGUF. Works with llama.cpp, ollama, LM Studio, and anything else that loads GGUFs.
Compatible with Reasoning Effort custom buttons. To use them, put the model in:
