Hypnos i1-8B is a professional reasoning model based on Nous Hermes 3 (Llama 3.1 8B), focusing on complex logic, chain-of-thought reasoning, and mathematical problem-solving. This model has conducted unique exploration in the field of hybrid quantum-classical machine learning, and improved the model's creativity and reasoning ability by introducing quantum noise injection.

Natural Language ProcessingTransformersEnglish

This is the Llamacpp imatrix quantized version of the Qwen3-VL-2B-Thinking model, providing files of various quantization types that can run efficiently in different hardware environments. This model is a multimodal vision-language model with 2B parameters and has the ability of chain-of-thought reasoning.

MultimodalGguf

This is a 4-bit quantized version converted from the Qwen3-VL-32B-Thinking model, specifically optimized for the MLX framework. This model is a multimodal vision-language model with a parameter scale of 32B. It has the ability of chain-of-thought reasoning and can process both image and text inputs simultaneously to generate high-quality text responses.

MultimodalTransformers

Qwen3-VL-8B-Thinking is an 8-billion-parameter multimodal large language model developed by the Qwen team at Alibaba Cloud. It is designed for deep multimodal reasoning, supporting visual understanding, long context processing, and structured chain-of-thought generation, and performs excellently in complex reasoning tasks.

MultimodalMlx

This is a GGUF format version converted from the Qwen/Qwen3-4B-Thinking-2507 model, using Q8_0 quantization, which can be used compatibly with llama.cpp. This model has chain-of-thought reasoning ability and has 4 billion parameters.

Natural Language ProcessingTransformers

PromptEnhancer-32B is a large language model with 32B parameters that supports multiple languages. It is specifically designed for tasks such as text-to-image, prompt enhancement, prompt rewriting, and chain-of-thought. This version provides GGUF format files with various quantization types, facilitating deployment and use in different hardware environments.

MultimodalTransformersMultiple Languages

This is the 4-bit quantized version of the Qwen3-Next-80B-A3B-Thinking model in MLX format, a large language model optimized for Apple Silicon, with 80 billion parameters and chain-of-thought reasoning ability.

Natural Language ProcessingMlx

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

MiMo-VL is a compact and powerful vision-language model that combines a native resolution ViT encoder, an MLP projector, and the MiMo-7B language model. It performs excellently in tasks such as multimodal reasoning. This model shows outstanding performance in multiple benchmark tests, has a chain-of-thought control function, and significantly improves the user experience.

MultimodalTransformers

This is the 3-bit quantization version of the Qwen3-235B-A22B-Thinking-2507 model, optimized and converted for the MLX framework. The original model is a large language model developed by the Alibaba Qwen team, with a scale of 235 billion parameters and support for chain-of-thought reasoning ability.

Natural Language ProcessingMlx

A 4-bit quantized version based on the Qwen3-235B-A22B-Thinking-2507 model, optimized for Apple chips using the MLX framework. It is a high-performance large language model with chain-of-thought reasoning capabilities.

Natural Language ProcessingTransformers

A LoRA fine-tuned version based on Qwen3-1.7B, which enhances the reasoning ability for complex logic and mathematical tasks through adaptive reasoning and thinking program techniques, supporting reasoning methods such as chain-of-thought and leap-of-thought.

Natural Language ProcessingSafetensorsOther

DeepSeek-R1-Llama-8B-F32-GGUF is the quantized version of DeepSeek-R1-Distill-Llama-8B, trained directly with reinforcement learning, featuring capabilities such as self-verification, reflection, and generating extended chain-of-thought reasoning.

Natural Language ProcessingTransformersEnglish

Stockmark-2-VL-100B-beta is a Japanese-specific vision-language model with 100 billion parameters, equipped with chain-of-thought (CoT) reasoning ability and can be used for document reading and comprehension.

MultimodalTransformersMultiple Languages

ReasonGen-R1 is an autoregressive image generation model that integrates chain-of-thought reasoning. It enhances the logic and quality of image generation through SFT and RL.

MultimodalTransformers

N1 is a small experimental Chain-of-Thought (COT) model developed by GoofyLM, built on the LLaMA architecture and focused on step-by-step reasoning problems.

Natural Language ProcessingTransformersEnglish

Cutting-edge mathematical reasoning model in the AceMath series, excelling at solving English math problems using Chain-of-Thought (CoT) reasoning.

Natural Language ProcessingSafetensorsEnglish

360 Zhinao 3-7B-O1.5 is a long chain-of-thought model open-sourced by Qihoo 360, fine-tuned based on 360 Zhinao 3-7B-Instruct, supporting complex reasoning tasks.

Natural Language ProcessingTransformersMultiple Languages

A large language model fine-tuned based on Google's Gemma-3 27B, specializing in chain-of-thought reasoning and code generation tasks, with optimized GPU memory and system memory management.

Natural Language ProcessingSafetensors

Phi-4 Reasoning is a cutting-edge open-weight reasoning model based on Phi-4, fine-tuned with supervised chain-of-thought trajectory datasets and trained via reinforcement learning, specializing in mathematics, science, and programming skills.

Natural Language ProcessingTransformersMultiple Languages