Qwopus3.5-v3.5/v3 Collection 🌟Qwopus3.5-v3.5 is the latest model in the Claude series. • 14 items • Updated 7 days ago • 103
JANG Quantized - GGUF for MLX Collection MLX models at full speed, GGUF quality. MiniMax M2.7: 88-95.5% MMLU. Requires MLX Studio. @dealignai • 30 items • Updated 19 days ago • 7
High Quality Uncensored - GGUF on MLX Collection These are the empirically proven highest quality uncensored models on MLX. • 26 items • Updated 20 days ago • 28
LLM in a flash: Efficient Large Language Model Inference with Limited Memory Paper • 2312.11514 • Published Dec 12, 2023 • 264