Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory β’ 15 items β’ Updated Jul 10 β’ 211
EXAONE-Deep Collection EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding β’ 10 items β’ Updated Jul 7 β’ 94
Jina Reader-LM Collection Convert HTML content to LLM-friendly Markdown/JSON content β’ 4 items β’ Updated Jul 20 β’ 18
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. β’ 9 items β’ Updated Feb 7 β’ 185