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’ 19 items β’ Updated 3 days ago β’ 13
Running on CPU Upgrade 13k 13k Open LLM Leaderboard π Track, rank and evaluate open LLMs and chatbots
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M β’ 16 items β’ Updated Feb 20 β’ 252
Whisper Collection OpenAI Whisper speech recognition models in MLX format β’ 48 items β’ Updated Oct 1, 2024 β’ 43