MiniMax-M2-AWQ is a quantized version based on the MiniMaxAI/MiniMax-M2 model, achieving efficient text generation through the vLLM framework. This model uses the AWQ quantization technology, significantly reducing memory usage and improving inference speed while maintaining model performance. It supports a 32K context length and tool call functionality.

Natural Language ProcessingTransformers

NanoAgent is a compact large intelligent language model with 135 million parameters and an 8k context length. It is specifically optimized for tool calls and instruction following, and can run efficiently on personal devices, supporting lightweight inference and ReAct-style interactions.

Natural Language ProcessingMlxEnglish

Qwen3-Next-80B-A3B-Instruct is an efficient sparse mixture of experts model developed by the Tongyi Qianwen team. It has a total of 80 billion parameters, with only 3 billion active parameters. The model adopts an innovative hybrid attention mechanism and a MoE architecture with an extremely low activation rate, significantly improving inference efficiency while maintaining strong performance. It natively supports a context length of 262,000 tokens and can be extended to 1 million tokens.

Natural Language ProcessingTransformers

Megrez 2-3x7B-A3B is a device-native large language model that adopts the Mixture of Experts (MoE) architecture, combining the accuracy of MoE and the compactness of dense models. The model is trained on 8T token data, has a context length of 32K, and plans to improve inference and agent capabilities in the future.

Natural Language ProcessingGgufMultiple 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

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

MobileLLM-Pro is a 1-billion-parameter efficient device-side language model launched by Meta, optimized for mobile devices, supporting a context length of 128k and providing high-quality inference capabilities. This model is trained using knowledge distillation technology, outperforming models of the same scale in multiple benchmark tests, and supporting nearly lossless 4-bit quantization.

Natural Language ProcessingTransformersEnglish

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

This is a high-quality quantized version of Moonshot AI's Kimi-K2-Instruct-0905 model, using the HQ4_K quantization method. It is specifically optimized for inference performance, supports a context length of 75,000, and is suitable for text generation tasks.

Natural Language ProcessingGgufOther

This is the GGUF quantized version of the NVIDIA Nemotron Nano 12B v2 model, which uses a hybrid Mamba - 2 and Transformer architecture, supports multilingual inference and chat functions, has 12 billion parameters, and supports a context length of up to 128K.

Natural Language ProcessingTransformersMultiple Languages

Schematron-8B is a long context extraction model launched by Inference.net, focusing on converting noisy HTML into clean, typed JSON that conforms to custom schemas. This model can handle lengthy HTML with up to 128K tokens and output valid JSON data that 100% conforms to the specified JSON schema.

Natural Language ProcessingTransformers

Cogito v2 is a generative hybrid inference model fine-tuned by instructions. It uses iterative distillation and amplification training methods and performs excellently in coding, STEM, instruction following, etc. It supports over 30 languages and a 128k context length.

Natural Language ProcessingTransformers

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model based on Meta Llama-3.3-70B-Instruct. It has enhanced inference, chat preference, and agent task capabilities through multi-stage post-training. It uses neural architecture search technology to significantly improve efficiency while maintaining high accuracy, and supports a context length of 128K tokens and multi-language processing.

Natural Language ProcessingTransformersEnglish

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model derived from Meta Llama-3.3-70B-Instruct and a significant upgrade to the v1 version. This model excels in inference, human dialogue preference, and agent tasks (such as RAG and tool calls). It supports a context length of 128K tokens and achieves a good balance between accuracy and efficiency.

Natural Language ProcessingTransformersEnglish

Qwen3-235B-A22B-Thinking-2507-AWQ is a quantized version based on the Qwen/Qwen3-235B-A22B-Thinking-2507 base model. It performs excellently in inference tasks and has better general capabilities and long context understanding capabilities. This model uses a mixture of experts architecture, with a total of 235B parameters and 22B activated parameters, and supports a context length of 256K.

Natural Language ProcessingTransformers

Llama-3.3-Nemotron-Super-49B-v1.5 is an efficient large language model developed by NVIDIA, derived from Meta Llama-3.3-70B-Instruct. This model performs excellently in inference, chat interaction, and agent tasks. It significantly reduces memory usage through neural architecture search technology and supports a context length of 128K tokens. Its capabilities in multiple aspects such as mathematics, code, science, and tool invocation have been enhanced.

Natural Language ProcessingTransformersEnglish

Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model based on Meta Llama-3.3-70B-Instruct. It has enhanced inference and non-inference capabilities through multi-stage post-training. It supports a context length of 128K tokens and strikes a good balance between accuracy and efficiency, making it suitable for inference, chatting, and agent tasks.

Natural Language ProcessingTransformersEnglish

GTA1 is a state-of-the-art GUI positioning model trained based on Reinforcement Learning (GRPO). It achieves precise interface element positioning by directly motivating actionable responses rather than lengthy inferences.

MultimodalTransformers

An efficient inference model fine-tuned based on Qwen 30B-A3B (MOE), achieving nearly double the speed improvement by reducing the number of experts, supporting multiple quantization formats and a 40K context length.

Natural Language ProcessingTransformers

Phi-3.5-mini-instruct is a lightweight and advanced open-source model built on the dataset used by Phi-3, focusing on high-quality, inference-rich data. It supports a 128K token context length and has powerful multilingual and long-context processing capabilities.

Natural Language ProcessingTransformersOther