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

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

This is a professional quantized version of the Qwen3-Omni model with 31.7B parameters. It uses advanced INT8+FP16 mixed-precision quantization technology, reducing memory usage by over 50%. It supports intelligent GPU/CPU hybrid inference, enabling large multimodal models to run efficiently on consumer-grade hardware.

MultimodalSafetensorsMultiple Languages

Qwen3-Next-80B-A3B-Instruct is the latest generation of large language model developed by the Tongyi Qianwen team at Alibaba. It adopts an innovative hybrid attention mechanism and a highly sparse mixture-of-experts architecture. While maintaining a total of 80B parameters, only 3B parameters are activated, achieving efficient context modeling and inference acceleration. It natively supports a context length of 262K and can be extended to 1M tokens.

Natural Language ProcessingTransformers

NVIDIA Nemotron Nano 9B v2 is a high-performance large language model developed by NVIDIA. It adopts the Mamba2-Transformer hybrid architecture, supports multilingual inference and chat tasks, and performs excellently in multiple benchmark tests. It especially supports the runtime 'thinking' budget control function.

Natural Language ProcessingTransformersMultiple Languages

MiniCPM4.1-8B GGUF is an efficient large language model designed specifically for edge devices. It has carried out systematic innovations in four key dimensions: model architecture, training data, training algorithm, and inference system, achieving extreme efficiency improvement. It supports a context length of 65,536 tokens and a hybrid inference mode.

Natural Language ProcessingTransformersMultiple 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

NVIDIA Nemotron Nano 12B v2 is a large language model trained from scratch by NVIDIA, designed for both inference and non-inference tasks. It adopts a hybrid Mamba2-Transformer architecture, supports multiple languages, has controllable inference capabilities, and can generate inference processes or directly give answers according to user needs.

Natural Language ProcessingTransformersMultiple Languages

NVIDIA-Nemotron-Nano-9B-v2 is a large language model newly trained by NVIDIA, a unified model designed for both inference and non-inference tasks. It adopts the Mamba2 - Transformer hybrid architecture, supports multiple languages, and has controllable inference capabilities. Users can control the display of the model's inference process through system prompts. The model performs excellently in multiple benchmark tests and is commercially available.

Natural Language ProcessingTransformersMultiple Languages

DeepSeek-V3.1 is a large language model developed by DeepSeek-AI and is an upgraded version of DeepSeek-V3. This model supports both hybrid thinking mode and non-thinking mode, and performs excellently in tool invocation, code generation, mathematical reasoning, etc., supporting a context length of 128K.

Natural Language ProcessingTransformers

NVIDIA Nemotron Nano 12B v2 is a large language model trained from scratch by NVIDIA, designed for both inference and non-inference tasks. This model adopts a hybrid architecture that combines Mamba-2 and attention layers, supports multilingual processing, and can control inference capabilities through system prompts.

Natural Language ProcessingTransformersMultiple Languages

NVIDIA-Nemotron-Nano-9B-v2 is a large language model trained from scratch by NVIDIA, designed for both inference and non-inference tasks. It adopts the Mamba2 - Transformer hybrid architecture, supports multilingual processing, has controllable inference capabilities, allows users to specify the thinking budget, and performs excellently in commercial applications and AI agent systems.

Natural Language ProcessingTransformersMultiple Languages

GLM-4.5-Air-AWQ-FP16Mix is an efficient text generation model obtained by quantizing the GLM-4.5-Air model. It uses a hybrid quantization technique of AWQ and FP16 and is suitable for large-scale language model inference scenarios in multi-GPU environments.

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

Falcon-H1 is a new family of large language models developed by the Technology Innovation Institute of the United Arab Emirates. It adopts a hybrid architecture that combines the Transformer attention mechanism and the state space model (SSMs), with excellent long-context memory ability and computational efficiency. This series of models offers various configurations with parameters ranging from 0.5B to 34B, and performs excellently in tasks such as inference, mathematics, and multilingual tasks.

Natural Language ProcessingTransformersMultiple Languages

The Linglong Linear Preview is a hybrid linear sparse large language model open-sourced by InclusionAI, with a total of 17.1B parameters and 3.0B activated parameters. This model implements long-text reasoning based on a hybrid linear attention mechanism, achieving near-linear computational complexity and near-constant space complexity during inference.

Natural Language ProcessingSafetensorsMultiple Languages

Nemotron-H-4B-Instruct-128K is a large language model with 4 billion parameters developed by NVIDIA. It uses a hybrid architecture, supports a 128K long context, and is optimized for scenarios such as chatting, instruction following, and tool calls. It supports multiple languages, including Chinese, English, Japanese, etc., a total of 10 languages.

Natural Language ProcessingTransformersEnglish

Llama-SEA-LION-v3.5-70B-R is a hybrid-function large language model optimized for Southeast Asian languages, supporting 13 languages with capabilities in complex reasoning and general text generation.

Natural Language ProcessingTransformersMultiple Languages

Nemotron-H-56B-Base-8K is a large language model developed by NVIDIA, featuring a hybrid Mamba-Transformer architecture, supporting 8K context length and multilingual text generation.

Natural Language ProcessingTransformersMultiple Languages

The NVIDIA Nemotron-H-47B-Base-8K is a large language model (LLM) developed by NVIDIA, designed for text completion tasks. It features a hybrid architecture primarily composed of Mamba-2 and MLP layers, with only five attention layers.

Natural Language ProcessingTransformersMultiple Languages