# Chat optimization

This is the MLX format version of the THUDM/GLM-4-32B-0414 model, processed with 4-bit DWQ quantization, suitable for efficient inference on Apple silicon devices.

An optimized 8-bit quantized version of Qwen3-8B, designed for efficient inference on the MLX framework

INT8 quantized version of Qwen2.5-7B-Instruct, suitable for multilingual scenarios in both commercial and research applications, optimized for memory requirements and computational throughput.

A chat model fine-tuned by H2O.ai with 4 billion parameters, supporting text generation tasks and capable of offline operation on mobile phones.

A 2B-parameter chat and instruction model optimized for Spanish, supporting text generation, dialogue, and Q&A tasks