Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing Paper • 2512.23611 • Published Dec 29, 2025 • 6
Unsloth Dynamic 2.0 Quants Collection New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 86 items • Updated 1 day ago • 530
My fine-tuned model yay Collection I fine-tune all these thing at kaggle (OR IN MY CURRENT 5060 YAY) • 4 items • Updated Dec 3, 2025 • 1
🧠 Reasoning datasets Collection Datasets with reasoning traces for math and code released by the community • 24 items • Updated May 19, 2025 • 188
Quantile model that I found funny Collection Some cool small LLM full 14 quantile. • 0 items • Updated Sep 2, 2025 • 1
gpt-oss-20b-pruned-GGUF Collection Bascially GPT OSS but for low end device, format in GGUF • 4 items • Updated Sep 2, 2025 • 1
GPT-OSS Pruned Experts (4.2B-20B) [IF, Science, Math, etc.] Collection Complete collection of domain-specialized GPT-OSS models (1-32 experts) optimized for science, math, medicine, law, safety, and instruction following. • 8 items • Updated Aug 13, 2025 • 11
Recommended large models Collection This collection contains some of the recent models larger than ~25B parameters that should be high quality and reliable • 15 items • Updated Nov 27, 2024 • 54
Recommended small models Collection This is everything recent smaller than ~25B parameters that are high quality/reputable • 19 items • Updated Nov 30, 2024 • 180