Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory โข 15 items โข Updated Mar 12 โข 218
EXAONE-Deep Collection EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding โข 10 items โข Updated Jul 7, 2025 โข 97
Jina Reader-LM Collection Convert HTML content to LLM-friendly Markdown/JSON content โข 4 items โข Updated Jul 20, 2025 โข 19
Dolphin 3.0 Collection Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. โข 9 items โข Updated Feb 7, 2025 โข 201