# MLX optimization

DiffuCoder-7B-cpGRPO-8bit is a code generation model converted to MLX format, based on apple/DiffuCoder-7B-cpGRPO, and is specifically designed to provide developers with an efficient code generation tool.

ERNIE-4.5-21B-A3B-PT-8bit is an 8-bit quantized version of Baidu's ERNIE-4.5-21B-A3B-PT model, converted to MLX format and suitable for Apple Silicon devices.

DiffuCoder-7B-cpGRPO-4bit is a 4-bit quantized version converted from the Apple DiffuCoder-7B-cpGRPO model, optimized for the MLX framework.

A 5-bit quantized version converted from Tencent's Hunyuan A13B large model, suitable for the MLX framework on Apple chips

The 4-bit quantization version of Tencent Hunyuan A13B large language model, suitable for instruction following tasks

Jan-nano-8bit is an 8-bit quantized version converted from the Menlo/Jan-nano model, optimized for the MLX framework and suitable for text generation tasks.

This is a 4-bit quantized version converted from the Qwen3-235B-A22B-8bit model, optimized for the MLX framework and suitable for text generation tasks.

This is an 8-bit quantized version in MLX format converted from the DeepSeek-R1-0528-Qwen3-8B model, suitable for text generation tasks.

4-bit DWQ quantized version of the Llama 3.3 70B instruction-tuned model, optimized for efficient inference on the MLX framework

This is a 4-bit quantized language model in MLX format, suitable for text generation tasks.

Devstral-Small-2505-8bit is an 8-bit quantized model converted from mistralai/Devstral-Small-2505, suitable for the MLX framework and supporting text generation tasks in multiple languages.

MedGemma-27B-Text-IT-BF16 is a large language model converted based on the MLX format, focusing on text processing tasks in the medical and health field.

MedGemma-4B-IT-8bit is an MLX format conversion version of the Google MedGemma model, focusing on visual language tasks in the medical field.

MedGemma-4B-IT-4bit is a vision-language model specifically designed for the medical field, supporting image and text processing, and suitable for tasks such as medical image analysis.

Devstral-Small-2505-bf16 is an MLX-format model converted from MistralAI's Devstral-Small-2505 model, supporting multiple language processing tasks.

A 4-bit quantized version of the Gemma 3 12B model, suitable for the MLX framework and supporting efficient text generation tasks.

This model is a 4-bit DWQ quantized version of Qwen3-4B, converted to the MLX format for easy text generation using the mlx library.

This is a 4-bit quantized model converted from Qwen/Qwen3-30B-A3B to MLX format, suitable for text generation tasks.

Qwen3-30B-A3B-4bit-DWQ-0508 is a 4-bit quantized model converted from Qwen/Qwen3-30B-A3B to MLX format, suitable for text generation tasks.

This is a 4-bit quantized version in MLX format converted from the Microsoft Phi-4-mini-reasoning model, suitable for text generation tasks.

4-bit quantized version based on Qwen3-1.7B, a lightweight large language model optimized for the MLX framework

Qwen3-1.7B-4bit is a 4-bit quantized version of the Tongyi Qianwen 1.7B model, which has been converted to the MLX framework format for efficient operation on Apple Silicon devices.

Dia-1.6B-6bit is a 6-bit quantized version based on Dia-1.6B, optimized for the MLX framework as a text-to-speech model.

Dia-1.6B-4bit is a 4-bit quantized text-to-speech model based on the MLX format, converted from nari-labs/Dia-1.6B.

Gemma 3 27B IT QAT BF16 is a version of the Gemma series of models released by Google. It has undergone quantization-aware training (QAT) and is converted to the BF16 format, suitable for the MLX framework.

Gemma 3 27B IT QAT 8bit is an MLX-format model converted from Google's Gemma 3 27B model, supporting image-to-text tasks.

This model is converted from ds4sd/SmolDocling-256M-preview to the MLX format, supporting image-text-to-text tasks.

This is a 4-bit quantized version converted from the allenai/OLMo-2-0325-32B-Instruct model, optimized for the MLX framework and suitable for text generation tasks.

This is the MLX 4-bit quantized version of the DeepSeek-R1-Distill-Qwen-32B model, designed for efficient inference on Apple silicon devices

This is a 4-bit quantized 135M parameter small language model, suitable for text generation tasks in resource-constrained environments.