Z-Image-Re-Turbo is a text-to-image generation model that has been optimized for de-reduction and re-acceleration based on the Z-Image-De-Turbo model. This model aims to balance the convenience during training and the speed during inference. It restores the fast generation ability close to the original Turbo model while maintaining the same training-friendly features as Z-Image-De-Turbo, enabling it to be perfectly compatible with a large number of trained LoRA models in the Z-Image ecosystem.

MultimodalDiffusers

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

VibeThinker-1.5B is a 1.5-billion-parameter dense language model launched by Weibo AI. It is fine-tuned based on Qwen2.5-Math-1.5B and is specifically designed for mathematical and algorithmic coding problems. Trained using the 'Spectrum to Signal Principle' framework, it outperforms larger models in multiple math competition tests. The training cost is approximately $7,800, and it supports an output of up to about 40k tokens.

Natural Language ProcessingTransformersMultiple Languages

PokeeResearch - 7B is a 7 - billion - parameter in - depth research agent model developed by Pokee AI. It combines Reinforcement Learning from AI Feedback (RLAIF) and a powerful reasoning framework, enabling reliable, aligned, and scalable research - level reasoning in tool - enhanced large language models. It is suitable for complex multi - step research workflows.

Natural Language ProcessingTransformersEnglish

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

Apriel-1.5-15b-Thinker is a multimodal reasoning model developed by the ServiceNow SLAM Lab, with a parameter scale of 15 billion. It has powerful text and image understanding and reasoning capabilities, adopting a chained reasoning mode of 'think-answer', aiming to achieve performance comparable to large models with a smaller model scale.

MultimodalTransformers

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

Apertus is a fully open multilingual large language model developed by Swiss AI. It has parameter scales of 8 billion and 70 billion, supports over 1000 languages and long context processing, and only uses fully compliant open training data. Its performance can rival that of closed-source models.

Natural Language ProcessingTransformersOther

This is the quantized version of the Tesslate/UIGEN-FX-4B-Preview model, aiming to make large language models easier to deploy and use through quantization technology, realizing the concept of 'Making knowledge accessible to everyone'.

Natural Language ProcessingGguf

This is a quantized version based on the Huihui-Hunyuan-MT-Chimera-7B model, aiming to make large language models easier to deploy and use through quantization technology, enabling knowledge to be accessible to everyone.

Natural Language ProcessingGguf

This project provides a quantized version of Tencent's Hunyuan-MT-7B large language model. Through model compression technology, it reduces the computing and storage requirements, aiming to make knowledge accessible to everyone and make high-performance AI models more popular and user - friendly.

Natural Language ProcessingGguf

LFM2-Audio-1.5B is the first end-to-end audio foundation model launched by Liquid AI, designed specifically for low-latency and real-time conversations. With only 1.5 billion parameters, this model can achieve seamless conversational interactions, and its capabilities can rival those of models with much larger parameter scales.

MultimodalSafetensorsEnglish

This is a large language model with 70B parameters merged using the Linear DELLA method. Based on the Llama-3.1-Nemotron-lorablated-70B base model, it integrates multiple high-performance Llama-3.3-70B variant models, aiming to provide more powerful language understanding and generation capabilities.

Natural Language ProcessingTransformers

GoldDiamondGold-70b is a large language model merged from multiple pre-trained language models using the mergekit tool. This model adopts the SCE merging method, based on cogito-v2, and integrates 17 different 70B parameter-scale models, aiming to combine the advantages of each model and provide intelligent text generation and dialogue capabilities.

Natural Language ProcessingTransformers

Cthulhu 24B 1.1 GGUF is a large language model fused based on the Mistral Small series of models, integrating 17 different model components. It has the capabilities of creative writing, uncensored dialogue, and rich language interaction. Inspired by the Cthulhu mythos, this model aims to provide a'super fusion' experience that goes beyond the capabilities of a single model.

Natural Language ProcessingTransformersEnglish

Devstral 1.1 is an intelligent large language model jointly developed by Mistral AI and All Hands AI, specifically designed for software engineering tasks. This model performs excellently in the SWE-bench benchmark test, ranking first among open-source models. It has 24 billion parameters and a long context window of 128k tokens.

Natural Language ProcessingSafetensorsMultiple Languages

The Deep Ignorance Model Suite is a collection of 18 large language models with 6.9 billion parameters each. It aims to study methods of preventing models from learning unsafe technical capabilities (such as CBRN-related capabilities) by filtering pretrained data. This suite demonstrates that filtering data can effectively avoid the learning of bad knowledge while maintaining general performance and having anti-tampering capabilities.

Natural Language ProcessingTransformersEnglish

This is a quantized version of the Qwen3-14B model by Huihui AI. It aims to make large language models more lightweight through model compression technology, reduce hardware requirements, and make knowledge acquisition more popular and convenient.

Natural Language ProcessingGguf

xLAM-2 is a series of large action models developed by Salesforce, focusing on multi-turn dialogue and function calling capabilities, serving as the core component of AI agents.

Natural Language ProcessingTransformersEnglish

The NeuralLake iSA-03 Mini 3B is an advanced AI model developed by NeuralLake Technology, combining the direct response capabilities of traditional large language models with automated multi-step reasoning, supporting ultra-long context processing of 256K tokens.

Natural Language ProcessingTransformers