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

LFM2-8B-A1B-qx86-hi-mlx is an efficient inference model based on the MLX format, converted from LiquidAI/LFM2-8B-A1B. This model adopts a mixture-of-experts architecture and demonstrates卓越的 efficiency in inference tasks. It is particularly擅长 at complex logical reasoning tasks and supports multilingual processing.

Natural Language ProcessingMlxMultiple Languages

Leporis-Qwen3-Radiation-1.7B is a model focused on reasoning, fine-tuned based on Qwen, used for precise reasoning and optimizing token probabilities. This model enhances the multilingual balanced generation ability across mathematics and general reasoning, and specializes in event-driven logic, structured analysis, and precise probabilistic modeling.

Natural Language ProcessingTransformersMultiple Languages

This is the GGUF quantized version of Alibaba's Qwen series large language model with 8 billion parameters, designed for advanced reasoning, intelligent agent behavior, and multilingual tasks, and can be used with llama.cpp and compatible tools.

Natural Language ProcessingGgufMultiple Languages

This is the GGUF quantized version of the Qwen/Qwen3-4B language model, a large language model with 4 billion parameters developed by Alibaba's Tongyi series. It is designed for consumer-grade hardware and supports powerful reasoning, intelligent agent workflows, and multilingual interaction.

Natural Language ProcessingGgufMultiple Languages

NVIDIA Nemotron Nano 12B v2 is a large language model developed by NVIDIA, which adopts the Mamba2-Transformer hybrid architecture and has 12 billion parameters. This model supports multilingual processing, performs excellently in multiple benchmark tests, is particularly good at reasoning tasks, and supports runtime reasoning budget control.

Natural Language ProcessingTransformersMultiple Languages

Qwen3-42B-A3B-2507 is a large language model with 42B parameters based on the Qwen3 architecture. It performs excellently in code generation and text generation tasks, supports multilingual processing, and has enhanced reasoning ability. This version has been specially optimized and shows performance improvements compared to previous versions in multiple benchmark tests.

Natural Language ProcessingMlxMultiple Languages

NexaAI/Qwen3-4B is a large language model with 4 billion parameters based on the Qwen3 series. It supports seamless switching between thinking mode and non-thinking mode and performs excellently in reasoning, instruction following, intelligent agent capabilities, and multilingual support.

Natural Language ProcessingGguf

NexaAI/Qwen3-0.6B is a 0.6B parameter language model based on the Qwen3 series, which performs excellently in reasoning, instruction following, and multilingual support. It supports seamless switching between thinking mode and non-thinking mode, and is suitable for complex logical reasoning and efficient general dialogue.

Natural Language ProcessingGguf

Qwen3-30B-A3B-Instruct-2507 is a 30.5 billion parameter mixture of experts model launched by Alibaba Cloud. It uses a non-thinking mode and performs excellently in instruction following, logical reasoning, text understanding, mathematics and science, coding, and tool usage. It supports a 262K long context and multilingual processing.

Natural Language ProcessingTransformers

Cogito v2 is a generative large language model fine-tuned with instructions, adopting a mixture-of-experts architecture and having 109 billion parameters. This model supports multilingual processing and long-context reasoning, and performs excellently in fields such as coding and STEM. It supports commercial use.

Natural Language ProcessingTransformers

Cogito v2 is a generative large language model based on instruction tuning, with hybrid reasoning ability, supporting a 128k context length and multilingual processing. This model adopts the Iterative Distillation and Amplification (IDA) training strategy and performs excellently in tasks such as coding, STEM, and instruction following.

Natural Language ProcessingTransformers

EXAONE-4.0-32B is a multilingual large model that combines advanced quantization technology with an efficient architecture. It has excellent text generation and reasoning capabilities and supports English, Korean, and Spanish.

Natural Language ProcessingTransformersMultiple Languages

SauerkrautLM-Reason-EuroColBERT is a powerful retriever based on the Late Interaction architecture. It learns complex reasoning patterns from synthetic data through knowledge distillation technology. With 210 million parameters, it performs excellently in multilingual reasoning retrieval and can be deployed on standard infrastructure without compression trade - offs.

Natural Language ProcessingSafetensorsOther

Qwen3-0.6B is a large language model based on the Qwen3 series. It supports text generation and has features such as unique thinking mode switching, powerful reasoning ability, and multilingual support.

Natural Language ProcessingGguf

A multilingual text generation model that performs quantization processing based on the HelpingAI's Dhanishtha-2.0-preview model, supporting multiple scenarios such as reasoning and dialogue.

Natural Language ProcessingTransformersMultiple Languages

Dhanishtha 2.0 is a breakthrough reasoning AI model developed by HelpingAI. It supports multilingual text generation, with intermediate thinking ability and multi - stage thinking process.

Natural Language ProcessingGgufMultiple Languages

Qwen3 - 32B is the latest large language model in the Qwen series, with 32.8 billion parameters. It has made breakthroughs in reasoning, instruction following, intelligent agent capabilities, and multilingual support, and supports seamless switching between thinking mode and non - thinking mode.

Natural Language ProcessingSafetensors

Blitzar-Coder-4B-F.1 is an efficient multilingual coding model fine-tuned based on Qwen3-4B, supporting more than 10 programming languages and having excellent code generation, debugging, and reasoning capabilities.

Natural Language ProcessingTransformersMultiple Languages

Magistral-Small-2506 is a small and efficient inference model built on Mistral Small 3.1, with 24 billion parameters, supporting multilingual and long-chain reasoning.

Natural Language ProcessingSafetensorsMultiple Languages