# MLX framework optimization

Kimi-K2-Instruct-4bit is a 4-bit quantized model converted from moonshotai/Kimi-K2-Instruct, suitable for the MLX framework.

The 4-bit quantized version of Qwen3-30B-A3B, suitable for efficient inference on the MLX framework

This is an MLX format model converted from Mistral-Small-3.2-24B-Instruct-2506, suitable for instruction following tasks.

This is a 4-bit quantized version converted from the SWE-bench/SWE-agent-LM-32B model, specifically optimized for software engineering tasks.

MLX format model converted from google/gemma-3-12b-it-qat-q4_0-unquantized, supporting image-text generation tasks

Gemma 3 4B IT QAT 4bit is a 4-bit quantized large language model trained with Quantization-Aware Training (QAT), based on the Gemma 3 architecture and optimized for the MLX framework.

A 4-bit quantized model converted from meta-llama/Llama-4-Maverick-17B-128E-Instruct, supporting multilingual text generation tasks

This is a multimodal model based on Llama-3.2-11B-Vision-Instruct, which supports image and text input and generates text output.