This model is a mixture of experts model after 25% uniform pruning of GLM-4.5-Air using the REAP method. It has been converted to a 4-bit quantized version in the MLX format, suitable for efficient inference on Apple chip devices.

Natural Language ProcessingTransformersEnglish

LFM2-8B-A1B is an 8-bit quantized MLX build version optimized for Apple Silicon chips, adopting the Mixture of Experts (MoE) architecture. It has approximately 8 billion total parameters, with about 1 billion parameters activated per token, and supports fast inference on the device side.

Natural Language ProcessingMlxEnglish

The 5-bit quantized version of the IBM Granite-4.0-H-Tiny model, optimized for Apple silicon chips. It uses a hybrid architecture of Mamba-2 and soft attention, combined with a Mixture of Experts model (MoE), to achieve efficient inference while maintaining high quality.

Natural Language ProcessingMlxMultiple Languages

IBM Granite-4.0-H-Tiny is a hybrid Mamba-2/Transformer model optimized for Apple silicon chips, using 3-bit quantization technology, and is designed for long context, efficient inference, and enterprise use. This model combines the Mamba-2 architecture with the Mixture of Experts (MoE) technology, significantly reducing memory usage while maintaining expressiveness.

Natural Language ProcessingMlxMultiple Languages

KAT-Dev is a multilingual natural language processing model developed by Kwaipilot. It supports a variety of multilingual interaction tasks and provides efficient and accurate language processing capabilities. This version has been optimized with 8-bit quantization by the MLX team and specifically optimized for Apple Silicon chips.

Natural Language ProcessingTransformersOther

GLM-4.6-4bit is a 4-bit quantized version converted from the zai-org/GLM-4.6 model using the mlx-lm tool. It is specifically optimized for Apple Silicon chips and supports Chinese and English text generation tasks.

Natural Language ProcessingMlxMultiple Languages

This is a large language model in MLX format converted from opendatalab/MinerU2.5-2509-1.2B, with a parameter scale of 1.2 billion. It is specifically optimized for Apple Silicon chips and supports FP16 precision inference.

Natural Language ProcessingTransformersMultiple Languages

Jinx GPT OSS 20B MXFP4 MLX is a large language model with 20 billion parameters converted based on the MLX framework. It is optimized using mixed-precision quantization technology and is suitable for efficient inference on Apple chip devices.

Natural Language ProcessingMlx

This is an MLX format version converted from the NousResearch/Hermes-4-14B model, supporting multiple quantization levels (2 - 8 bits), and is a large language model optimized for Apple chips.

Natural Language ProcessingMlxEnglish

This model is a 4-bit quantized MLX format model converted from the original Qwen/Qwen3-Next-80B-A3B-Instruct model using mlx-lm version 0.28.0. It is optimized for Apple chips and supports efficient text generation tasks.

Natural Language ProcessingMlx

Qwen3-Next-80B-A3B-Instruct is a large-scale language model developed by the Tongyi Qianwen team of Alibaba Cloud. It has been optimized with 4-bit quantization using the MLX framework and specifically optimized for Apple chip devices to provide efficient inference capabilities.

Natural Language ProcessingTransformers

This is a 4-bit mxfp4 quantized version optimized for Apple MLX based on the Qwen3-Next-80B-A3B-Thinking base model. It is specifically optimized for Apple silicon chips and can achieve efficient local inference on Mac devices, significantly reducing memory usage while maintaining good performance.

Natural Language ProcessingMlx

This is a large language model with 49B parameters based on the NVIDIA Nemotron architecture. It has been converted to the MLX format and undergone 4-bit quantization, specifically optimized for Apple Silicon chips to provide efficient text generation capabilities.

Natural Language ProcessingTransformersEnglish

This is a text embedding model converted to the MLX format, derived from Google's EmbeddingGemma-300m model. It is specifically designed for sentence similarity calculation and text embedding tasks. The model uses BF16 precision and is suitable for efficient inference on Apple chip devices.

Natural Language ProcessingSentence-transformers

MiniCPM4.1-8B-GGUF is a GGUF quantized format version of the MiniCPM4.1-8B model. It is an efficient large language model designed for edge devices, with 8 billion parameters, supporting integrated thinking, and can achieve more than 5 times the generation acceleration on typical edge chips.

Natural Language ProcessingTransformersMultiple Languages

Seed-OSS-36B-Instruct is a large language model developed by ByteDance-Seed, with 36 billion parameters and released under the Apache 2.0 open-source license. This model is built on the transformers library, supports vllm and mlx technology optimization, and has undergone 8-bit quantization specifically for Apple Silicon chips, providing efficient text generation capabilities.

Natural Language ProcessingTransformers

This is an MLX format version converted from the NVIDIA Llama-3.3-Nemotron-Super-49B-v1.5 model. It is converted to the 8-bit quantized format using the mlx-lm 0.26.3 tool and is specifically optimized for Apple Silicon chips, supporting efficient local inference.

Natural Language ProcessingTransformersEnglish

This is the 4-bit quantized version of the DeepSeek-V3.1-Base model, converted using the mlx-lm tool and specifically optimized for Apple Silicon chips, providing efficient large language model inference capabilities.

Natural Language ProcessingMlx

Marvis is an advanced conversational voice model designed for real-time streaming text-to-speech synthesis. It focuses on efficiency and ease of use, supporting high-quality real-time voice synthesis on consumer devices such as Apple chips, iPhones, iPads, and Macs.

Audio ProcessingTransformersEnglish

Gemma 3 270M Instruct is a lightweight text generation model launched by Google. It is optimized for Apple Silicon chips based on MLX technology, providing efficient dialogue and instruction-following capabilities.

Natural Language ProcessingTransformers