ttindall/Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF
Text Generation • 27B • Updated • 644k • 214
TCrypt
ttindall
AI & ML interests
abliteration · uncensored LLMs · GGUF quantization · MTP / speculative decoding · tool-calling fine-tunes · GRPO · memory layers · single-GPU local inference · open evals · video and image diffusion
Recent Activity
liked a model about 3 hours ago
peculiar-ragdoll/Dirk-Qwen3.8-27B-GGUF liked a model 1 day ago
MiniMaxAI/MiniMax-H3-Image upvoted a paper 2 days ago
CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning ReuseOrganizations
None yet