QwenEdit2509 is a specially designed Low - Rank Adaptation (LoRA) model focused on image color processing. It can desaturate images and reduce contrast, creating a flat, ungraded look similar to a camera's log profile while preserving details in highlights and shadows.

Computer VisionDiffusersEnglish

Qwen3-Next-80B-A3B-Thinking is an 80B parameter large language model that has undergone 4-bit quantization and is specifically optimized for Apple Silicon. It has been selected for the LM Studio Community Model Highlights Program and focuses on text generation tasks.

Natural Language ProcessingTransformers

This is a 4-bit quantized version of Google's Gemma 3 270M Instruct model, specifically optimized for Apple chips using the MLX framework. This model is a lightweight yet powerful language model suitable for various text generation tasks and participates in the LM Studio Community Model Highlights Program.

Natural Language ProcessingTransformers

Based on the Qwen architecture, the Qwen3-4B-Instruct-2507 model is launched by the community and 4-bit quantized using MLX, specifically optimized for Apple chips. This model provides an efficient and high-performance solution for text generation tasks and is part of the LM Studio Community Model Highlights Program.

Natural Language ProcessingTransformers

Based on the Qwen3-Coder-30B-A3B-Instruct model from the Qwen team, 6-bit quantization is performed through MLX and optimized specifically for Apple Silicon. This model focuses on code generation and understanding tasks and is part of the LM Studio Community Model Highlights Program.

Natural Language ProcessingTransformers

A large-scale language model launched by the Qwen team, processed by MLX quantization and optimized for Apple chips, providing an efficient text generation experience. It is selected for the LM Studio Community Model Highlights Program.

Natural Language ProcessingTransformers

This is a quantized version of the Qwen3 235B A22B Thinking 2507 model, implemented through the quantization technology of llama.cpp. It can efficiently run text generation tasks in resource-constrained environments and is part of the LM Studio Community Model Highlights Program.

Natural Language ProcessingGguf

This is the GGUF quantized version of the NVIDIA OpenReasoning Nemotron 7B model, specifically designed for text generation tasks. This model is provided through the LM Studio Community Model Highlights Program, supporting efficient inference and deployment.

Natural Language ProcessingGguf

Baidu ERNIE-4.5-21B-A3B is a community version based on the ERNIE-4.5-21B-A3B-PT base model. It uses MLX for 6-bit quantization and is specifically optimized for Apple chips. This model is presented in the LM Studio Community Model Highlights Program and has efficient inference performance and good compatibility.

Natural Language ProcessingTransformersMultiple Languages

lametta is an anime-style model specifically designed for generating images of girls with a low head-to-body ratio. After multiple versions of iterative optimization, it particularly focuses on the performance of eye highlights and the detailed depiction of fingers. The latest v2012 version enhances the richness of character expressions while maintaining the consistent style.

Computer VisionDiffusersJapanese