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 13 hours ago
MiniMaxAI/MiniMax-H3-Image upvoted a paper 1 day ago
CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse reacted to danielhanchen's post with 🔥 1 day ago
Qwen3.8-Flash-Next GGUFs now run faster with less thinking and less token use.
Unsloth Dynamic V3.1 GGUFs bring thinking & token use to match 95% of full precision Qwen3.8-Flash.
Results: 50% fewer tokens + 15% higher accuracy vs same size quants.
GGUF: https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF
Analysis/Guide: https://unsloth.ai/docs/models/qwen3.8-nextOrganizations
None yet
works very nice
❤️ 1
1
#2 opened 15 days ago
by 
unk1911