# MLX Optimization

DiffuCoder-7B-cpGRPO-6bit is a text generation model converted based on the MLX format, focusing on code and text diffusion tasks.

ERNIE-4.5-0.3B-PT-bf16 is a version of the ERNIE series models developed by Baidu, with a parameter scale of 0.3B and trained using bf16 precision.

This is a large language model converted based on the MLX format, suitable for text generation tasks.

This model is an MLX format version converted from deepseek-ai/deepseek-r1-0528-Qwen3-8B, suitable for local inference on Apple devices.

MedGemma-27B-Text-IT-4bit is an MLX-format model converted from Google's MedGemma-27B-Text-IT model, specifically optimized for medical and clinical reasoning tasks.

Qwen3-32B-8bit is an 8-bit quantized version of the Qwen3-32B model, designed for text generation tasks and released by mlx-community.

This model is converted from Qwen/Qwen3-30B-A3B to the MLX format, supporting 8-bit quantization and suitable for text generation tasks.

Qwen3-8B-bf16 is an MLX format model converted from Qwen/Qwen3-8B, supporting text generation tasks.

Qwen3-30B-A3B-8bit is an MLX format conversion version of the Qwen/Qwen3-30B-A3B model, supporting efficient operation on Apple chips.

An 8-bit quantized large language model in MLX format converted from Qwen/Qwen3-8B, suitable for text generation tasks

This model is a 4-bit quantized version of Qwen3-32B in MLX format, optimized for efficient operation on Apple Silicon devices.

UI-TARS-1.5-7B-4bit is a multimodal model focused on image-text-to-text conversion tasks, supporting the English language.

This model is an 8-bit quantized MLX format conversion from THUDM/GLM-4-32B-0414, supporting Chinese and English text generation tasks.

This is a 3-bit quantized text-to-speech model in MLX format, supporting multiple languages.

VL-Rethinker-7B-8bit is a multimodal model based on Qwen2.5-VL-7B-Instruct, supporting visual question answering tasks.

This model is a multimodal vision-language model converted from Qwen2.5-VL-7B-Instruct, supporting 8-bit quantization and suitable for visual question-answering tasks.

VL-Rethinker-72B-4bit is a multimodal model based on Qwen2.5-VL-7B-Instruct, supporting visual question answering tasks, and has been converted to MLX format for efficient operation on Apple devices.

Gemma 3 27B IT QAT 4bit is an MLX-format model converted from Google's original model, supporting image-to-text tasks.

This is an MLX-converted version of the Google Gemma 3 27B IT model, supporting image-text-to-text tasks.