Popular repositories Loading

1. turboquant-mlx turboquant-mlx Public

   TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

   Python 42 6

2. mlx-lm mlx-lm Public

   Forked from ml-explore/mlx-lm

   Run LLMs with MLX

   Python 1

3. mlx mlx Public

   Forked from ml-explore/mlx

   MLX: An array framework for Apple silicon

   C++

4. ggml-ane ggml-ane Public

   Objective-C++

5. vllm-mlx vllm-mlx Public

   Forked from waybarrios/vllm-mlx

   OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …

   Python