This is a 4-bit quantized version converted from the moonshotai/Kimi-Linear-48B-A3B-Instruct model, optimized for the Apple MLX framework, providing efficient text generation capabilities.

Natural Language ProcessingMlx

Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods in various scenarios, including short and long contexts, as well as reinforcement learning extension mechanisms. It can effectively solve the problem of low efficiency of traditional attention mechanisms in long context tasks and bring more efficient solutions to fields such as natural language processing.

Natural Language ProcessingTransformers

Kimi Linear is an efficient hybrid linear attention architecture that outperforms traditional full attention methods in short context, long context, and reinforcement learning scenarios. It optimizes attention computation through the Kimi Delta Attention (KDA) mechanism, significantly improving performance and hardware efficiency, and is particularly good at handling long context tasks up to 1 million tokens.

Natural Language ProcessingTransformers

This is the MLX format conversion version of the moonshotai/Kimi-K2-Instruct-0905 model, using the innovative DQ3_K_M dynamic 3-bit quantization technology, specifically optimized for Apple Silicon Mac devices. It significantly reduces memory usage while maintaining performance close to 4-bit quantization.

Natural Language ProcessingMlx

This is a quantized version of the moonshotai/Kimi-K2-Instruct-0905 model, dedicated to making knowledge accessible to everyone. This project provides optimized model weights for easy deployment and use on various hardware.

Natural Language ProcessingGguf

Based on the moonshotai/Kimi-K2-Instruct-0905 base model, a large language model dynamically quantized using the improved MLX 0.26. Through an innovative dynamic quantization strategy, it significantly reduces hardware requirements while maintaining excellent performance and can run efficiently on a single M3 Ultra device.

Natural Language ProcessingMlx

This is the GGUF format quantized version of the moonshotai/Kimi-K2-Instruct-0905 model, using the ik_llama.cpp branch for optimal quantization. The model adopts a mixture of experts architecture, supports Chinese dialogue and text generation tasks, and has been optimized with various quantization schemes to significantly reduce memory usage while maintaining high quality.

Natural Language ProcessingGgufOther

Kimi-VL-A3B-Thinking-2506 is a multimodal visual language model developed by MoonshotAI. It supports the joint understanding and reasoning of images and text, has the ability of chain-of-thought reasoning, and can handle complex visual language tasks.

MultimodalGguf

Kimi-K2 Dynamic MLX is a text generation project built on the moonshotai/Kimi-K2-Instruct model, using the optimized MLX library to achieve efficient quantization performance. This model runs on a single M3 Ultra machine with 512GB RAM, supports multiple quantization methods, and shows excellent perplexity metrics in tests.

Natural Language ProcessingMlx

Kimi - K2 - Instruct is a quantized version based on the moonshotai/Kimi - K2 - Instruct model, aiming to make knowledge more widely accessible to the public.

Natural Language ProcessingGguf

Kimi-Dev-72B-8bit is an 8-bit quantized version converted from moonshotai/Kimi-Dev-72B, a text generation model suitable for the MLX framework.

Natural Language ProcessingMlxOther

Kimi-Dev-72B-4bit-DWQ is a 4-bit quantized large language model converted from moonshotai/Kimi-Dev-72B, suitable for the MLX framework.

Natural Language ProcessingMlxOther

Kimi K2 is an advanced Mixture of Experts (MoE) language model with 32 billion active parameters and 1 trillion total parameters, optimized for agent capabilities.

Natural Language ProcessingTransformers

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

Natural Language ProcessingMlx

Kimi-Dev-72B-4bit is a 4-bit quantized large language model converted from moonshotai/Kimi-Dev-72B and optimized for the MLX framework.

Natural Language ProcessingMlxOther

Kimi-Dev-72B-5bit is a 5-bit quantized large language model converted from moonshotai/Kimi-Dev-72B, suitable for the MLX framework on Apple devices.

Natural Language ProcessingMlxOther

Kimi K2 is an advanced Mixture of Experts (MoE) language model with 32 billion active parameters and a total of 1 trillion parameters, optimized for agent capabilities.

Natural Language ProcessingTransformers

Kimi K2 is an advanced Mixture of Experts (MoE) language model with 32 billion active parameters and 1 trillion total parameters, optimized for agent capabilities.

Natural Language ProcessingTransformers

Kimi-Dev-72B is a large-scale language model developed by moonshotai. It is optimized through GGUF quantization and offers multiple quantization versions to meet different hardware requirements.

Natural Language ProcessingGguf

Kimi-VL-A3B-Thinking-2506 is an upgraded version of Kimi-VL-A3B-Thinking, with significant improvements in multimodal reasoning, visual perception and understanding, video scene processing, etc. It supports higher-resolution images and can achieve more intelligent thinking while consuming fewer tokens.

MultimodalTransformers