This is a compact Spanish-to-English translation model optimized for accuracy and efficiency. The model size is 386MB, supporting a context length of 4096 tokens, and can efficiently and accurately complete translation tasks with an average response time of approximately 245ms.

Natural Language ProcessingGgufMultiple Languages

Apertus is a fully open multilingual large language model developed by Swiss AI, offering two parameter scales of 7 billion and 8 billion. This model supports over 1000 languages, uses fully compliant and open training data, and its performance can rival that of closed-source models. Apertus was pre-trained on 15T tokens and adopts a phased curriculum training method, supporting a context length of up to 65,536 tokens.

Natural Language ProcessingTransformersOther

PaDT Pro 3B is a multimodal large language model based on Qwen2.5VL-3B. It adopts a unified paradigm of decodable block tokens and can directly generate text and visual outputs, achieving advanced performance in multiple visual perception and understanding tasks.

MultimodalTransformersMultiple Languages

GLM 4.6 is a quantized model optimized for a configuration of 128GB memory + single GPU. It uses the IQ_K quantization method, providing better quality and performance than the mainstream llama.cpp at the same size. This model needs to be used with ik_llama.cpp. On a configuration of 128GB dual-channel DDR5 memory, a single CCD Ryzen 7000 processor + a single 3090 graphics card, the text generation speed can reach approximately 6.8 tokens per second.

Natural Language ProcessingGgufMultiple Languages

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

This is a large language model in MLX format converted from the Qwen3-Next-80B model, with the ability to handle ultra-long contexts of 1 million tokens. The model uses a unique qx65 quantization formula, focusing on emotional resonance rather than simple technical optimization. It can perceive the emotions behind questions and generate more humanized responses.

Natural Language ProcessingMlx

Granite-4.0-Micro-Base is a decoder-only long-context language model developed by IBM. It is trained from scratch on approximately 15 trillion tokens and adopts a four-stage training strategy. This model is designed for various text generation tasks and supports multilingual and fill-in-the-middle code completion functions.

Natural Language ProcessingTransformers

Granite-4.0-H-Tiny-Base is a decoder-only long-context language model developed by IBM. It uses a mixture-of-experts architecture and has been trained in four stages on approximately 23 trillion tokens. It supports multilingual text generation and code completion tasks.

Natural Language ProcessingTransformers

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

Qwen3-Next-80B-A3B-Instruct-AWQ-4bit is an efficient version based on the Qwen3-Next-80B-A3B-Instruct model with 4-bit AWQ quantization. This model adopts a hybrid attention mechanism and a highly sparse mixture-of-experts (MoE) architecture, supporting a context length of up to 262K tokens. It significantly reduces the computational resource requirements while maintaining high performance.

Natural Language ProcessingTransformers

LLaDA-MoE is a new type of mixture-of-experts language model constructed based on the diffusion principle. It is the first open-source MoE diffusion large language model, pre-trained from scratch on approximately 20 trillion tokens. It has a total of 7 billion parameters, and only 1.4 billion parameters are activated during inference. It performs excellently in tasks such as code generation and mathematical reasoning.

Natural Language ProcessingTransformers

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

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

Kuaishou Keye-VL is a cutting - edge multimodal large language model developed by the Kuaishou Keye team, which performs excellently in video understanding, visual perception, and reasoning tasks. The 1.5 version reaches a new height in video understanding, image perception, and reasoning ability through innovative fast - slow video encoding strategies, LongCoT cold - start data pipelines, and reinforcement learning training strategies, and supports an extended context length of up to 128k tokens.

MultimodalSafetensorsMultiple Languages

Seed-OSS is an open-source large language model series developed by the ByteDance Seed team. It has powerful long context processing, reasoning, and agent interaction capabilities. Trained with only 12T tokens, it performs excellently in multiple public benchmark tests and supports native long context processing of up to 512K.

Natural Language ProcessingTransformers

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

Seed-OSS is an open-source large language model series developed by the ByteDance Seed team. It has powerful long context processing, reasoning, agent interaction capabilities, and general performance. This model was trained with only 12T tokens and performed excellently in multiple public benchmark tests.

Natural Language ProcessingTransformersMultiple Languages

Moonlight is a Mixture of Experts (MoE) model with a total of 16B parameters and 3B active parameters, trained based on the Muon optimizer using 5.7T tokens. This model improves the current Pareto frontier, achieving better performance with fewer training FLOPs and excelling in multiple benchmark tests.

Natural Language ProcessingTransformers

Code Llama is a large language model with 70 billion parameters developed by Meta, specifically optimized for the Python programming language. This model is based on an optimized Transformer architecture and supports code synthesis and understanding tasks, with a maximum context length of 16k tokens.

Natural Language ProcessingPytorchOther