Qwopus3.5-v3 Collection 🌟Qwopus3.5-v3 is the latest model in the Claude series. • 12 items • Updated 3 days ago • 70
JANG Quantized - GGUF for MLX Collection MLX models at full speed, GGUF quality. MiniMax M2.7: 88-95.5% MMLU. Requires MLX Studio. @dealignai • 26 items • Updated about 12 hours ago • 6
High Quality Uncensored - GGUF on MLX Collection These are the empirically proven highest quality uncensored models on MLX. • 19 items • Updated 9 days ago • 12
LLM in a flash: Efficient Large Language Model Inference with Limited Memory Paper • 2312.11514 • Published Dec 12, 2023 • 264
Jean-Baptiste/camembert-ner-with-dates Token Classification • 0.1B • Updated Jun 16, 2023 • 198k • • 46