Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 29 days ago • 219
view article Article Querying Hugging Face Datasets with the DuckDB UI cfahlgren1 • Apr 3, 2025 • 18
view article Article Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques jmamou • Mar 24, 2025 • 20