CodeV is a 7-billion-parameter vision-language model fine-tuned based on Qwen2.5-VL-7B-Instruct. Through two-stage training of supervised fine-tuning (SFT) and reinforcement learning (RL) based on tool-aware policy optimization (TAPO), it aims to achieve reliable and interpretable visual reasoning. It represents visual tools as executable Python code and ensures the consistency between tool usage and question evidence through a reward mechanism, solving the problem of irrelevant tool invocation under high accuracy.

MultimodalTransformersMultiple Languages

This model is obtained through distillation training using the high-reasoning-difficulty Gemini 3 Pro preview dataset based on the Qwen3-4B-Thinking-2507 base model. It focuses on improving complex reasoning abilities in the fields of coding and science. Through training with specific datasets, it aims to efficiently transfer the reasoning abilities of large models (such as Gemini 3 Pro) to a smaller-scale model.

Natural Language ProcessingTransformers

Fyodor-Q3-8B-Instruct is a high-fidelity instruction-tuned model designed for intelligent reasoning and robust code generation. It is based on the Qwen3-8B architecture and trained with a high-rank LoRA configuration. It excels in planning before coding and is well-suited for complex software engineering tasks.

Natural Language ProcessingTransformersMultiple Languages

OpenMMReasoner is a fully transparent two-stage multimodal reasoning solution that covers supervised fine-tuning (SFT) and reinforcement learning (RL). By carefully constructing high-quality datasets, this solution surpasses powerful baseline models in multiple multimodal reasoning benchmark tests, laying a solid empirical foundation for future large-scale multimodal reasoning research.

MultimodalTransformers

This is a large language model with 30 billion parameters trained on the Claude Sonnet 4.5 reasoning dataset. It is specifically optimized for high-difficulty reasoning tasks and performs excellently in the fields of coding and science.

Natural Language ProcessingTransformersEnglish

This is a distilled model based on the Qwen3 30B A3B model, trained on the Claude Sonnet 4.5 high-reasoning-difficulty dataset. This model is specifically optimized for complex reasoning tasks and performs excellently in the fields of coding and science, with strong logical reasoning ability.

Natural Language ProcessingTransformersEnglish

ERNIE-4.5-VL-28B-A3B-Thinking AWQ - INT8 is a multimodal large language model based on Baidu's ERNIE-4.5 architecture. It achieves 8-bit precision through the AWQ quantization technology, significantly reducing memory requirements while maintaining high performance. This model performs excellently in visual reasoning, STEM problem-solving, image analysis, etc., and has powerful multimodal understanding and reasoning abilities.

MultimodalTransformersMultiple Languages

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-Next-80B-A3B-Thinking is a new-generation thinking large language model launched by the Tongyi Qianwen team. It adopts an innovative hybrid attention mechanism and a highly sparse MoE architecture. While maintaining efficient reasoning, it has powerful complex reasoning capabilities and natively supports a context length of 262K.

Natural Language ProcessingTransformers

A high-performance video generation model with 4-step reasoning based on LoRA. The LoRA weights are extracted from the Wan2.2 distilled model, featuring flexible deployment, efficient storage, and excellent generation quality.

MultimodalDiffusers

Qwen-SEA-LION-v4-32B-IT is a large Southeast Asian language model built on Qwen3-32B, specifically pre-trained and instruction fine-tuned for the Southeast Asian region. This model continues pre-training on the SEA-Pile v2 corpus containing 7 Southeast Asian languages and undergoes instruction fine-tuning on 8 million pairs of high-quality question-and-answer data, possessing strong multilingual understanding and reasoning abilities.

Natural Language ProcessingTransformersMultiple Languages

Nemotron-Flash-3B is a new hybrid small language model launched by NVIDIA, specifically designed for low-latency requirements in practical applications. This model demonstrates excellent performance in tasks such as mathematics, coding, and common-sense reasoning, and also has the characteristics of excellent low latency for small batches and high throughput for large batches.

Natural Language ProcessingTransformers

Bee-8B is an advanced fully open-source multimodal large language model that focuses on data quality and aims to narrow the performance gap with proprietary models. By using the high-quality Honey-Data-15M corpus and the advanced data processing pipeline HoneyPipe, it demonstrates excellent performance in complex reasoning and other aspects.

MultimodalTransformersEnglish

Frugal-Math-4B is a 4B parameter language model optimized for mathematical reasoning. It is trained using the Reinforcement Learning with Verification Reward (RLVR) method and can generate concise and verifiable mathematical solutions while maintaining high accuracy, significantly reducing the verbosity of reasoning.

Natural Language ProcessingTransformersMultiple Languages

The palmyra-mini series of models demonstrates excellent capabilities in the fields of complex reasoning and mathematical problem-solving, especially performing outstandingly in benchmark tests that require in-depth understanding and multi-step thinking. This model is proficient in solving elementary school-level math problems, achieving a high score of 0.818 in the gsm8k benchmark test, also obtaining a score of 0.818 in the MATH500 benchmark test, and a stable score of 0.6 in the AMC23 benchmark test.

Natural Language ProcessingTransformersMultiple Languages

Qwen3-Next-80B-A3B-Thinking-AWQ-4bit is a 4-bit version generated from the Qwen3-Next-80B-A3B-Thinking model through the AWQ quantization technology, which significantly improves the model's inference efficiency. This model adopts a hybrid attention mechanism and a highly sparse MoE architecture, and performs excellently in complex reasoning tasks. It supports a context length of up to 262K tokens.

Natural Language ProcessingTransformers

Qwen3-Next-80B-A3B-Instruct is the base model of the Qwen3-Next series. Through technologies such as the innovative hybrid attention mechanism and highly sparse mixture-of-experts layers, it achieves efficient modeling and reasoning acceleration in long text processing and demonstrates excellent performance in multiple benchmark tests.

Natural Language ProcessingTransformers

Ring-mini-2.0 is a high-performance inference MoE model deeply optimized based on the Ling 2.0 architecture. It has only 16 billion total parameters and 1.4 billion active parameters, yet it achieves comprehensive inference capabilities comparable to dense models below 10 billion scale. It performs excellently in logical reasoning, code generation, and math tasks, supports processing long contexts of up to 128,000 tokens, and enables high-speed generation of over 300 tokens per second.

Natural Language ProcessingSafetensors

This is the GGUF quantized version of the Qwen3-Code-Reasoning-4B model, specifically optimized for competition programming and code reasoning tasks. The model is trained on a high-quality code reasoning dataset, enhancing its ability to solve complex programming problems through detailed reasoning.

Natural Language ProcessingGgufEnglish

The GPT-OSS series is an open-weight model released by OpenAI, designed for powerful reasoning, agent tasks, and diverse developer use cases. The 120B version has 117 billion parameters (5.1 billion of which are active parameters), suitable for production environments and scenarios requiring high reasoning ability.

Natural Language ProcessingTransformers